RESUMO
Object detection is a computer vision task that involves localisation and classification of objects in an image. Video data implicitly introduces several challenges, such as blur, occlusion and defocus, making video object detection more challenging in comparison to still image object detection, which is performed on individual and independent images. This paper tackles these challenges by proposing an attention-heavy framework for video object detection that aggregates the disentangled features extracted from individual frames. The proposed framework is a two-stage object detector based on the Faster R-CNN architecture. The disentanglement head integrates scale, spatial and task-aware attention and applies it to the features extracted by the backbone network across all the frames. Subsequently, the aggregation head incorporates temporal attention and improves detection in the target frame by aggregating the features of the support frames. These include the features extracted from the disentanglement network along with the temporal features. We evaluate the proposed framework using the ImageNet VID dataset and achieve a mean Average Precision (mAP) of 49.8 and 52.5 using the backbones of ResNet-50 and ResNet-101, respectively. The improvement in performance over the individual baseline methods validates the efficacy of the proposed approach.
RESUMO
Purpose: Diabetic foot is a common complication associated with diabetes mellitus (DM) leading to ulcerations in the feet. Due to diabetic neuropathy, most patients have reduced sensitivity to pain. As a result, minor injuries go unnoticed and progress into ulcers. The timely detection of potential ulceration points and intervention is crucial in preventing amputation. Changes in plantar temperature are one of the early signs of ulceration. Previous studies have focused on either binary classification or grading of DM severity, but neglect the holistic consideration of the problem. Moreover, multi-class studies exhibit severe performance variations between different classes. Methods: We propose a new convolutional neural network for discrimination between non-DM and five DM severity grades from plantar thermal images and compare its performance against pre-trained networks such as AlexNet and related works. We address the lack of data and imbalanced class distribution, prevalent in prior work, achieving well-balanced classification performance. Results: Our proposed model achieved the best performance with a mean accuracy of 0.9827, mean sensitivity of 0.9684 and mean specificity of 0.9892 in combined diabetic foot detection and grading. Conclusion: To the best of our knowledge, this study sets a new state-of-the-art in plantar foot thermogram detection and grading, while being the first to implement a holistic multi-class classification and grading solution. Reliable automatic thermogram grading is a first step towards the development of smart health devices for DM patients.