GCPDFFNet: Small Object Detection for Rice Blast Recognition.

Early detection of rice blast disease is pivotal to ensure rice yield. We collected in situ images of rice blast and constructed a rice blast dataset based on variations in lesion shape, size, and color. Given that rice blast lesions are small and typically exhibit round, oval, and fusiform shapes, we proposed a small object detection model named GCPDFFNet (global context-based parallel differentiation feature fusion network) for rice blast recognition. The GCPDFFNet model has three global context feature extraction modules and two parallel differentiation feature fusion modules. The global context modules are employed to focus on the lesion areas; the parallel differentiation feature fusion modules are used to enhance the recognition effect of small-sized lesions. In addition, we proposed the SCYLLA normalized Wasserstein distance loss function, specifically designed to accelerate model convergence and improve the detection accuracy of rice blast disease. Comparative experiments were conducted on the rice blast dataset to evaluate the performance of the model. The proposed GCPDFFNet model outperformed the baseline network CenterNet, with a significant increase in mean average precision from 83.6 to 95.4% on the rice blast test set while maintaining a satisfactory frames per second drop from 147.9 to 122.1. Our results suggest that the GCPDFFNet model can accurately detect in situ rice blast disease while ensuring the inference speed meets the real-time requirements.

OD-YOLO: Robust Small Object Detection Model in Remote Sensing Image with a Novel Multi-Scale Feature Fusion.

As remote sensing technology has advanced, the use of satellites and similar technologies has become increasingly prevalent in daily life. Now, it plays a crucial role in hydrology, agriculture, and geography. Nevertheless, because of the distinct qualities of remote sensing, including expansive scenes and small, densely packed targets, there are many challenges in detecting remote sensing objects. Those challenges lead to insufficient accuracy in remote sensing object detection. Consequently, developing a new model is essential to enhance the identification capabilities for objects in remote sensing imagery. To solve these constraints, we have designed the OD-YOLO approach that uses multi-scale feature fusion to improve the performance of the YOLOv8n model in small target detection. Firstly, traditional convolutions have poor recognition capabilities for certain geometric shapes. Therefore, in this paper, we introduce the Detection Refinement Module (DRmodule) into the backbone architecture. This module utilizes Deformable Convolutional Networks and the Hybrid Attention Transformer to strengthen the model's capability for feature extraction from geometric shapes and blurred objects effectively. Meanwhile, based on the Feature Pyramid Network of YOLO, at the head of the model framework, this paper enhances the detection capability by introducing a Dynamic Head to strengthen the fusion of different scales features in the feature pyramid. Additionally, to address the issue of detecting small objects in remote sensing images, this paper specifically designs the OIoU loss function to finely describe the difference between the detection box and the true box, further enhancing model performance. Experiments on the VisDrone dataset show that OD-YOLO surpasses the compared models by at least 5.2% in mAP50 and 4.4% in mAP75, and experiments on the Foggy Cityscapes dataset demonstrated that OD-YOLO improved mAP by 6.5%, demonstrating outstanding results in tasks related to remote sensing images and adverse weather object detection. This work not only advances the research in remote sensing image analysis, but also provides effective technical support for the practical deployment of future remote sensing applications.

A Recursive Prediction-Based Feature Enhancement for Small Object Detection.

Transformer-based methodologies in object detection have recently piqued considerable interest and have produced impressive results. DETR, an end-to-end object detection framework, ingeniously integrates the Transformer architecture, traditionally used in NLP, into computer vision for sequence-to-sequence prediction. Its enhanced variant, DINO, featuring improved denoising anchor boxes, has showcased remarkable performance on the COCO val2017 dataset. However, it often encounters challenges when applied to scenarios involving small object detection. Thus, we propose an innovative method for feature enhancement tailored to recursive prediction tasks, with a particular emphasis on augmenting small object detection performance. It primarily involves three enhancements: refining the backbone to favor feature maps that are more sensitive to small targets, incrementally augmenting the number of queries for small objects, and advancing the loss function for better performance. Specifically, The study incorporated the Switchable Atrous Convolution (SAC) mechanism, which features adaptable dilated convolutions, to increment the receptive field and thus elevate the innate feature extraction capabilities of the primary network concerning diminutive objects. Subsequently, a Recursive Small Object Prediction (RSP) module was designed to enhance the feature extraction of the prediction head for more precise network operations. Finally, the loss function was augmented with the Normalized Wasserstein Distance (NWD) metric, tailoring the loss function to suit small object detection better. The efficacy of the proposed model is empirically confirmed via testing on the VISDRONE2019 dataset. The comprehensive array of experiments indicates that our proposed model outperforms the extant DINO model in terms of average precision (AP) small object detection.

Small Target Detection in Refractive Panorama Surveillance Based on Improved YOLOv8.

Panoramic imaging is increasingly critical in UAVs and high-altitude surveillance applications. In addressing the challenges of detecting small targets within wide-area, high-resolution panoramic images, particularly issues concerning accuracy and real-time performance, we have proposed an improved lightweight network model based on YOLOv8. This model maintains the original detection speed, while enhancing precision, and reducing the model size and parameter count by 10.6% and 11.69%, respectively. It achieves a 2.9% increase in the overall mAP@0.5 and a 20% improvement in small target detection accuracy. Furthermore, to address the scarcity of reflective panoramic image training samples, we have introduced a panorama copy-paste data augmentation technique, significantly boosting the detection of small targets, with a 0.6% increase in the overall mAP@0.5 and a 21.3% rise in small target detection accuracy. By implementing an unfolding, cutting, and stitching process for panoramic images, we further enhanced the detection accuracy, evidenced by a 4.2% increase in the mAP@0.5 and a 12.3% decrease in the box loss value, validating the efficacy of our approach for detecting small targets in complex panoramic scenarios.

Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8.

In this work, an object detection method using variable convolution-improved YOLOv8 is proposed to solve the problem of low accuracy and low efficiency in detecting spanning and irregularly shaped samples. Aiming at the problems of the irregular shape of a target, the low resolution of labeling frames, dense distribution, and the ease of overlap, a deformable convolution module is added to the original backbone network. This allows the model to deal flexibly with the problem of the insufficient perceptual field of the target corresponding to the detection point, and the situations of leakage and misdetection can be effectively improved. In order to solve the issue that small target detection is susceptible to image background and noise interference, the Sim-AM (simple parameter-free attention mechanism) module is added to the backbone network of YOLOv8, which enhances the attention to the underlying features and, thus, improves the detection accuracy of the model. More importantly, the Sim-AM module does not need to add parameters to the original network, which reduces the computation of the model. To address the problem of complex model structures that can lead to slower detection, the spatial pyramid pooling of the backbone network is replaced with focal modulation networks, which greatly simplifies the computation process. The experimental validation was carried out on the scrap steel dataset containing a large number of targets of multiple shapes and sizes. The results showed that the improved YOLOv8 network model improves the AP (average precision) by 2.1%, the mAP (mean average precision value) by 0.8%, and reduces the FPS (frames per second) by 5.4, which meets the performance requirements of real-time industrial inspection.

Analysis of Varroa Mite Colony Infestation Level Using New Open Software Based on Deep Learning Techniques.

Varroa mites, scientifically identified as Varroa destructor, pose a significant threat to beekeeping and cause one of the most destructive diseases affecting honey bee populations. These parasites attach to bees, feeding on their fat tissue, weakening their immune systems, reducing their lifespans, and even causing colony collapse. They also feed during the pre-imaginal stages of the honey bee in brood cells. Given the critical role of honey bees in pollination and the global food supply, controlling Varroa mites is imperative. One of the most common methods used to evaluate the level of Varroa mite infestation in a bee colony is to count all the mites that fall onto sticky boards placed at the bottom of a colony. However, this is usually a manual process that takes a considerable amount of time. This work proposes a deep learning approach for locating and counting Varroa mites using images of the sticky boards taken by smartphone cameras. To this end, a new realistic dataset has been built: it includes images containing numerous artifacts and blurred parts, which makes the task challenging. After testing various architectures (mainly based on two-stage detectors with feature pyramid networks), combination of hyperparameters and some image enhancement techniques, we have obtained a system that achieves a mean average precision (mAP) metric of 0.9073 on the validation set.

Enhancing Badminton Game Analysis: An Approach to Shot Refinement via a Fusion of Shuttlecock Tracking and Hit Detection from Monocular Camera.

Extracting the flight trajectory of the shuttlecock in a single turn in badminton games is important for automated sports analytics. This study proposes a novel method to extract shots in badminton games from a monocular camera. First, TrackNet, a deep neural network designed for tracking small objects, is used to extract the flight trajectory of the shuttlecock. Second, the YOLOv7 model is used to identify whether the player is swinging. As both TrackNet and YOLOv7 may have detection misses and false detections, this study proposes a shot refinement algorithm to obtain the correct hitting moment. By doing so, we can extract shots in rallies and classify the type of shots. Our proposed method achieves an accuracy of 89.7%, a recall rate of 91.3%, and an F1 rate of 90.5% in 69 matches, with 1582 rallies of the Badminton World Federation (BWF) match videos. This is a significant improvement compared to the use of TrackNet alone, which yields 58.8% accuracy, 93.6% recall, and 72.3% F1 score. Furthermore, the accuracy of shot type classification at three different thresholds is 72.1%, 65.4%, and 54.1%. These results are superior to those of TrackNet, demonstrating that our method effectively recognizes different shot types. The experimental results demonstrate the feasibility and validity of the proposed method.

SD-YOLOv8: An Accurate Seriola dumerili Detection Model Based on Improved YOLOv8.

Accurate identification of Seriola dumerili (SD) offers crucial technical support for aquaculture practices and behavioral research of this species. However, the task of discerning S. dumerili from complex underwater settings, fluctuating light conditions, and schools of fish presents a challenge. This paper proposes an intelligent recognition model based on the YOLOv8 network called SD-YOLOv8. By adding a small object detection layer and head, our model has a positive impact on the recognition capabilities for both close and distant instances of S. dumerili, significantly improving them. We construct a convenient S. dumerili dataset and introduce the deformable convolution network v2 (DCNv2) to enhance the information extraction process. Additionally, we employ the bottleneck attention module (BAM) and redesign the spatial pyramid pooling fusion (SPPF) for multidimensional feature extraction and fusion. The Inner-MPDIoU bounding box regression function adjusts the scale factor and evaluates geometric ratios to improve box positioning accuracy. The experimental results show that our SD-YOLOv8 model achieves higher accuracy and average precision, increasing from 89.2% to 93.2% and from 92.2% to 95.7%, respectively. Overall, our model enhances detection accuracy, providing a reliable foundation for the accurate detection of fishes.

A Lightweight Remote Sensing Small Target Image Detection Algorithm Based on Improved YOLOv8.

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds.

A Multi-Scale-Enhanced YOLO-V5 Model for Detecting Small Objects in Remote Sensing Image Information.

As a typical component of remote sensing signals, remote sensing image (RSI) information plays a strong role in showing macro, dynamic and accurate information on the earth's surface and environment, which is critical to many application fields. One of the core technologies is the object detection (OD) of RSI signals (RSISs). The majority of existing OD algorithms only consider medium and large objects, regardless of small-object detection, resulting in an unsatisfactory performance in detection precision and the miss rate of small objects. To boost the overall OD performance of RSISs, an improved detection framework, I-YOLO-V5, was proposed for OD in high-altitude RSISs. Firstly, the idea of a residual network is employed to construct a new residual unit to achieve the purpose of improving the network feature extraction. Then, to avoid the gradient fading of the network, densely connected networks are integrated into the structure of the algorithm. Meanwhile, a fourth detection layer is employed in the algorithm structure in order to reduce the deficiency of small-object detection in RSISs in complex environments, and its effectiveness is verified. The experimental results confirm that, compared with existing advanced OD algorithms, the average accuracy of the proposed I-YOLO-V5 is improved by 15.4%, and the miss rate is reduced by 46.8% on the RSOD dataset.

T-YOLO: a lightweight and efficient detection model for nutrient buds in complex tea-plantation environments.

BACKGROUND: Quick and accurate detection of nutrient buds is essential for yield prediction and field management in tea plantations. However, the complexity of tea plantation environments and the similarity in color between nutrient buds and older leaves make the location of tea nutrient buds challenging. RESULTS: This research presents a lightweight and efficient detection model, T-YOLO, for the accurate detection of tea nutrient buds in unstructured environments. First, a lightweight module, C2fG2, and an efficient feature extraction module, DBS, are introduced into the backbone and neck of the YOLOv5 baseline model. Second, the head network of the model is pruned to achieve further lightweighting. Finally, the dynamic detection head is integrated to mitigate the feature loss caused by lightweighting. The experimental data show that T-YOLO achieves a mean average precision (mAP) of 84.1%, the total number of parameters for model training (Params) is 11.26 million (M), and the number of floating-point operations (FLOPs) is 17.2 Giga (G). Compared with the baseline YOLOv5 model, T-YOLO reduces Params by 47% and lowers FLOPs by 65%. T-YOLO also outperforms the existing optimal detection YOLOv8 model by 7.5% in terms of mAP. CONCLUSION: The T-YOLO model proposed in this study performs well in detecting small tea nutrient buds. It provides a decision-making basis for tea farmers to manage smart tea gardens. The T-YOLO model outperforms mainstream detection models on the public dataset, Global Wheat Head Detection (GWHD), which offers a reference for the construction of lightweight and efficient detection models for other small target crops. © 2024 Society of Chemical Industry.

Small Object Detection and Tracking: A Comprehensive Review.

Object detection and tracking are vital in computer vision and visual surveillance, allowing for the detection, recognition, and subsequent tracking of objects within images or video sequences. These tasks underpin surveillance systems, facilitating automatic video annotation, identification of significant events, and detection of abnormal activities. However, detecting and tracking small objects introduce significant challenges within computer vision due to their subtle appearance and limited distinguishing features, which results in a scarcity of crucial information. This deficit complicates the tracking process, often leading to diminished efficiency and accuracy. To shed light on the intricacies of small object detection and tracking, we undertook a comprehensive review of the existing methods in this area, categorizing them from various perspectives. We also presented an overview of available datasets specifically curated for small object detection and tracking, aiming to inform and benefit future research in this domain. We further delineated the most widely used evaluation metrics for assessing the performance of small object detection and tracking techniques. Finally, we examined the present challenges within this field and discussed prospective future trends. By tackling these issues and leveraging upcoming trends, we aim to push forward the boundaries in small object detection and tracking, thereby augmenting the functionality of surveillance systems and broadening their real-world applicability.

A Small Object Detection Algorithm for Traffic Signs Based on Improved YOLOv7.

Traffic sign detection is a crucial task in computer vision, finding wide-ranging applications in intelligent transportation systems, autonomous driving, and traffic safety. However, due to the complexity and variability of traffic environments and the small size of traffic signs, detecting small traffic signs in real-world scenes remains a challenging problem. In order to improve the recognition of road traffic signs, this paper proposes a small object detection algorithm for traffic signs based on the improved YOLOv7. First, the small target detection layer in the neck region was added to augment the detection capability for small traffic sign targets. Simultaneously, the integration of self-attention and convolutional mix modules (ACmix) was applied to the newly added small target detection layer, enabling the capture of additional feature information through the convolutional and self-attention channels within ACmix. Furthermore, the feature extraction capability of the convolution modules was enhanced by replacing the regular convolution modules in the neck layer with omni-dimensional dynamic convolution (ODConv). To further enhance the accuracy of small target detection, the normalized Gaussian Wasserstein distance (NWD) metric was introduced to mitigate the sensitivity to minor positional deviations of small objects. The experimental results on the challenging public dataset TT100K demonstrate that the SANO-YOLOv7 algorithm achieved an 88.7% mAP@0.5, outperforming the baseline model YOLOv7 by 5.3%.

UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios.

Unmanned aerial vehicle (UAV) object detection plays a crucial role in civil, commercial, and military domains. However, the high proportion of small objects in UAV images and the limited platform resources lead to the low accuracy of most of the existing detection models embedded in UAVs, and it is difficult to strike a good balance between detection performance and resource consumption. To alleviate the above problems, we optimize YOLOv8 and propose an object detection model based on UAV aerial photography scenarios, called UAV-YOLOv8. Firstly, Wise-IoU (WIoU) v3 is used as a bounding box regression loss, and a wise gradient allocation strategy makes the model focus more on common-quality samples, thus improving the localization ability of the model. Secondly, an attention mechanism called BiFormer is introduced to optimize the backbone network, which improves the model's attention to critical information. Finally, we design a feature processing module named Focal FasterNet block (FFNB) and propose two new detection scales based on this module, which makes the shallow features and deep features fully integrated. The proposed multiscale feature fusion network substantially increased the detection performance of the model and reduces the missed detection rate of small objects. The experimental results show that our model has fewer parameters compared to the baseline model and has a mean detection accuracy higher than the baseline model by 7.7%. Compared with other mainstream models, the overall performance of our model is much better. The proposed method effectively improves the ability to detect small objects. There is room to optimize the detection effectiveness of our model for small and feature-less objects (such as bicycle-type vehicles), as we will address in subsequent research.

Efficient-Lightweight YOLO: Improving Small Object Detection in YOLO for Aerial Images.

The most significant technical challenges of current aerial image object-detection tasks are the extremely low accuracy for detecting small objects that are densely distributed within a scene and the lack of semantic information. Moreover, existing detectors with large parameter scales are unsuitable for aerial image object-detection scenarios oriented toward low-end GPUs. To address this technical challenge, we propose efficient-lightweight You Only Look Once (EL-YOLO), an innovative model that overcomes the limitations of existing detectors and low-end GPU orientation. EL-YOLO surpasses the baseline models in three key areas. Firstly, we design and scrutinize three model architectures to intensify the model's focus on small objects and identify the most effective network structure. Secondly, we design efficient spatial pyramid pooling (ESPP) to augment the representation of small-object features in aerial images. Lastly, we introduce the alpha-complete intersection over union (α-CIoU) loss function to tackle the imbalance between positive and negative samples in aerial images. Our proposed EL-YOLO method demonstrates a strong generalization and robustness for the small-object detection problem in aerial images. The experimental results show that, with the model parameters maintained below 10 M while the input image size was unified at 640 × 640 pixels, the APS of the EL-YOLOv5 reached 10.8% and 10.7% and enhanced the APs by 1.9% and 2.2% compared to YOLOv5 on two challenging aerial image datasets, DIOR and VisDrone, respectively.

Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression.

Bounding box regression is a crucial step in object detection, directly affecting the localization performance of the detected objects. Especially in small object detection, an excellent bounding box regression loss can significantly alleviate the problem of missing small objects. However, there are two major problems with the broad Intersection over Union (IoU) losses, also known as Broad IoU losses (BIoU losses) in bounding box regression: (i) BIoU losses cannot provide more effective fitting information for predicted boxes as they approach the target box, resulting in slow convergence and inaccurate regression results; (ii) most localization loss functions do not fully utilize the spatial information of the target, namely the target's foreground area, during the fitting process. Therefore, this paper proposes the Corner-point and Foreground-area IoU loss (CFIoU loss) function by delving into the potential for bounding box regression losses to overcome these issues. First, we use the normalized corner point distance between the two boxes instead of the normalized center-point distance used in the BIoU losses, which effectively suppresses the problem of BIoU losses degrading to IoU loss when the two boxes are close. Second, we add adaptive target information to the loss function to provide richer target information to optimize the bounding box regression process, especially for small object detection. Finally, we conducted simulation experiments on bounding box regression to validate our hypothesis. At the same time, we conducted quantitative comparisons of the current mainstream BIoU losses and our proposed CFIoU loss on the small object public datasets VisDrone2019 and SODA-D using the latest anchor-based YOLOv5 and anchor-free YOLOv8 object detection algorithms. The experimental results demonstrate that YOLOv5s (+3.12% Recall, +2.73% mAP@0.5, and +1.91% mAP@0.5:0.95) and YOLOv8s (+1.72% Recall and +0.60% mAP@0.5), both incorporating the CFIoU loss, achieved the highest performance improvement on the VisDrone2019 test set. Similarly, YOLOv5s (+6% Recall, +13.08% mAP@0.5, and +14.29% mAP@0.5:0.95) and YOLOv8s (+3.36% Recall, +3.66% mAP@0.5, and +4.05% mAP@0.5:0.95), both incorporating the CFIoU loss, also achieved the highest performance improvement on the SODA-D test set. These results indicate the effectiveness and superiority of the CFIoU loss in small object detection. Additionally, we conducted comparative experiments by fusing the CFIoU loss and the BIoU loss with the SSD algorithm, which is not proficient in small object detection. The experimental results demonstrate that the SSD algorithm incorporating the CFIoU loss achieved the highest improvement in the AP (+5.59%) and AP75 (+5.37%) metrics, indicating that the CFIoU loss can also improve the performance of algorithms that are not proficient in small object detection.

MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario.

To tackle the challenges posed by dense small objects and fuzzy boundaries on unstructured roads in the mining scenario, we proposed an end-to-end small object detection and drivable area segmentation framework for open-pit mining. We employed a convolutional network backbone as a feature extractor for both two tasks, as multi-task learning yielded promising results in autonomous driving perception. To address small object detection, we introduced a lightweight attention module that allowed our network to focus more on the spatial and channel dimensions of small objects without impeding inference time. We also used a convolutional block attention module in the drivable area segmentation subnetwork, which assigned more weight to road boundaries to improve feature mapping capabilities. Furthermore, to improve our network perception accuracy of both tasks, we used weighted summation when designing the loss function. We validated the effectiveness of our approach by testing it on pre-collected mining data which were called Minescape. Our detection results on the Minescape dataset showed 87.8% mAP index, which was 9.3% higher than state-of-the-art algorithms. Our segmentation results surpassed the comparison algorithm by 1 percent in MIoU index. Our experimental results demonstrated that our approach achieves competitive performance.

STC-YOLO: Small Object Detection Network for Traffic Signs in Complex Environments.

The detection of traffic signs is easily affected by changes in the weather, partial occlusion, and light intensity, which increases the number of potential safety hazards in practical applications of autonomous driving. To address this issue, a new traffic sign dataset, namely the enhanced Tsinghua-Tencent 100K (TT100K) dataset, was constructed, which includes the number of difficult samples generated using various data augmentation strategies such as fog, snow, noise, occlusion, and blur. Meanwhile, a small traffic sign detection network for complex environments based on the framework of YOLOv5 (STC-YOLO) was constructed to be suitable for complex scenes. In this network, the down-sampling multiple was adjusted, and a small object detection layer was adopted to obtain and transmit richer and more discriminative small object features. Then, a feature extraction module combining a convolutional neural network (CNN) and multi-head attention was designed to break the limitations of ordinary convolution extraction to obtain a larger receptive field. Finally, the normalized Gaussian Wasserstein distance (NWD) metric was introduced to make up for the sensitivity of the intersection over union (IoU) loss to the location deviation of tiny objects in the regression loss function. A more accurate size of the anchor boxes for small objects was achieved using the K-means++ clustering algorithm. Experiments on 45 types of sign detection results on the enhanced TT100K dataset showed that the STC-YOLO algorithm outperformed YOLOv5 by 9.3% in the mean average precision (mAP), and the performance of STC-YOLO was comparable with that of the state-of-the-art methods on the public TT100K dataset and CSUST Chinese Traffic Sign Detection Benchmark (CCTSDB2021) dataset.

Aligned Matching: Improving Small Object Detection in SSD.

Although detecting small objects is critical in various applications, neural network models designed and trained for generic object detection struggle to do so with precision. For example, the popular Single Shot MultiBox Detector (SSD) tends to perform poorly for small objects, and balancing the performance of SSD across different sized objects remains challenging. In this study, we argue that the current IoU-based matching strategy used in SSD reduces the training efficiency for small objects due to improper matches between default boxes and ground truth objects. To address this issue and improve the performance of SSD in detecting small objects, we propose a new matching strategy called aligned matching that considers aspect ratios and center-point distance in addition to IoU. The results of experiments on the TT100K and Pascal VOC datasets show that SSD with aligned matching detected small objects significantly better without sacrificing performance on large objects or requiring extra parameters.

Yolo-Pest: An Insect Pest Object Detection Algorithm via CAC3 Module.

Insect pests have always been one of the main hazards affecting crop yield and quality in traditional agriculture. An accurate and timely pest detection algorithm is essential for effective pest control; however, the existing approach suffers from a sharp performance drop when it comes to the pest detection task due to the lack of learning samples and models for small pest detection. In this paper, we explore and study the improvement methods of convolutional neural network (CNN) models on the Teddy Cup pest dataset and further propose a lightweight and effective agricultural pest detection method for small target pests, named Yolo-Pest, for the pest detection task in agriculture. Specifically, we tackle the problem of feature extraction in small sample learning with the proposed CAC3 module, which is built in a stacking residual structure based on the standard BottleNeck module. By applying a ConvNext module based on the vision transformer (ViT), the proposed method achieves effective feature extraction while keeping a lightweight network. Comparative experiments prove the effectiveness of our approach. Our proposal achieves 91.9% mAP0.5 on the Teddy Cup pest dataset, which outperforms the Yolov5s model by nearly 8% in mAP0.5. It also achieves great performance on public datasets, such as IP102, with a great reduction in the number of parameters.