MME-YOLO: Multi-Sensor Multi-Level Enhanced YOLO for Robust Vehicle Detection in Traffic Surveillance.

As an effective means of solving collision problems caused by the limited perspective on board, the cooperative roadside system is gaining popularity. To improve the vehicle detection abilities in such online safety systems, in this paper, we propose a novel multi-sensor multi-level enhanced convolutional network model, called multi-sensor multi-level enhanced convolutional network architecture (MME-YOLO), with consideration of hybrid realistic scene of scales, illumination, and occlusion. MME-YOLO consists of two tightly coupled structures, i.e., the enhanced inference head and the LiDAR-Image composite module. More specifically, the enhanced inference head preliminarily equips the network with stronger inference abilities for redundant visual cues by attention-guided feature selection blocks and anchor-based/anchor-free ensemble head. Furthermore, the LiDAR-Image composite module cascades the multi-level feature maps from the LiDAR subnet to the image subnet, which strengthens the generalization of the detector in complex scenarios. Compared with YOLOv3, the enhanced inference head achieves a 5.83% and 4.88% mAP improvement on visual dataset LVSH and UA-DETRAC, respectively. Integrated with the composite module, the overall architecture gains 91.63% mAP in the collected Road-side Dataset. Experiments show that even under the abnormal lightings and the inconsistent scales at evening rush hours, the proposed MME-YOLO maintains reliable recognition accuracy and robust detection performance.

A Mobile Anchor Node Assisted RSSI Localization Scheme in Underwater Wireless Sensor Networks.

In this paper, a mobile anchor node assisted RSSI localization scheme in underwater wireless sensor networks (UWSNs) is proposed, which aims to improve location accuracy and shorten location time. First, to improve location accuracy, we design a support vector regression (SVR) based interpolation method to estimate the projection of sensor nodes on the linear trajectory of the mobile anchor node. The proposed method increases the accuracy of the nonlinear regression model of noisy measured data and synchronously decreases the estimation error caused by the discreteness of measured data. Second, to shorten location time, we develop a curve matching method to obtain the perpendicular distance from sensor nodes to the linear trajectory of the mobile anchor node. The location of the sensor node can be calculated based on the projection and the perpendicular distance. Compared with existing schemes that require the anchor node to travel at least two trajectories, the proposed scheme only needs one-time trajectory to locate sensor nodes, and the location time is shortened with the reduction in the number of trajectories. Finally, simulation results prove that the proposed scheme can obtain more accurate sensor node location in less time compared with the existing schemes.

A Cost-Effective Vehicle Localization Solution Using an Interacting Multiple Model-Unscented Kalman Filters (IMM-UKF) Algorithm and Grey Neural Network.

In this paper, we propose a cost-effective localization solution for land vehicles, which can simultaneously adapt to the uncertain noise of inertial sensors and bridge Global Positioning System (GPS) outages. First, three Unscented Kalman filters (UKFs) with different noise covariances are introduced into the framework of Interacting Multiple Model (IMM) algorithm to form the proposed IMM-based UKF, termed as IMM-UKF. The IMM algorithm can provide a soft switching among the three UKFs and therefore adapt to different noise characteristics. Further, two IMM-UKFs are executed in parallel when GPS is available. One fuses the information of low-cost GPS, in-vehicle sensors, and micro electromechanical system (MEMS)-based reduced inertial sensor systems (RISS), while the other fuses only in-vehicle sensors and MEMS-RISS. The differences between the state vectors of the two IMM-UKFs are considered as training data of a Grey Neural Network (GNN) module, which is known for its high prediction accuracy with a limited amount of samples. The GNN module can predict and compensate position errors when GPS signals are blocked. To verify the feasibility and effectiveness of the proposed solution, road-test experiments with various driving scenarios were performed. The experimental results indicate that the proposed solution outperforms all the compared methods.

A Highly Reliable and Cost-Efficient Multi-Sensor System for Land Vehicle Positioning.

In this paper, we propose a novel positioning solution for land vehicles which is highly reliable and cost-efficient. The proposed positioning system fuses information from the MEMS-based reduced inertial sensor system (RISS) which consists of one vertical gyroscope and two horizontal accelerometers, low-cost GPS, and supplementary sensors and sources. First, pitch and roll angle are accurately estimated based on a vehicle kinematic model. Meanwhile, the negative effect of the uncertain nonlinear drift of MEMS inertial sensors is eliminated by an H∞ filter. Further, a distributed-dual-H∞ filtering (DDHF) mechanism is adopted to address the uncertain nonlinear drift of the MEMS-RISS and make full use of the supplementary sensors and sources. The DDHF is composed of a main H∞ filter (MHF) and an auxiliary H∞ filter (AHF). Finally, a generalized regression neural network (GRNN) module with good approximation capability is specially designed for the MEMS-RISS. A hybrid methodology which combines the GRNN module and the AHF is utilized to compensate for RISS position errors during GPS outages. To verify the effectiveness of the proposed solution, road-test experiments with various scenarios were performed. The experimental results illustrate that the proposed system can achieve accurate and reliable positioning for land vehicles.

SC_LPR: Semantically Consistent LiDAR Place Recognition Based on Chained Cascade Network in Long-Term Dynamic Environments.

In large-scale long-term dynamic environments, high-frequency dynamic objects inevitably lead to significant changes in the appearance of the scene at the same location at different times, which is catastrophic for place recognition (PR). Therefore, how to eliminate the influence of dynamic objects to achieve robust PR has universal practical value for mobile robots and autonomous vehicles. To this end, we suggest a novel semantically consistent LiDAR PR method based on chained cascade network, called SC_LPR, which mainly consists of a LiDAR semantic image inpainting network (LSI-Net) and a semantic pyramid Transformer-based PR network (SPT-Net). Specifically, LSI-Net is a coarse-to-fine generative adversarial network (GAN) with a gated convolutional autoencoder as the backbone. To effectively address the challenges posed by variable-scale dynamic object masks, we integrate the updated Transformer block with mask attention and gated trident block into LSI-Net. Sequentially, in order to generate a discriminative global descriptor representing the point cloud, we design an encoder with pyramid Transformer block to efficiently encode long-range dependencies and global contexts between different categories in the inpainted semantic image, followed by an augmented NetVALD, a generalized VLAD (Vector of Locally Aggregated Descriptors) layer that adaptively aggregates salient local features. Last but not least, we first attempt to create a LiDAR semantic inpainting dataset, called LSI-Dataset, to effectively validate the proposed method. Experimental comparisons show that our method not only improves semantic inpainting performance by about 6%, but also improves PR performance in dynamic environments by about 8% compared to the representative optimal baseline. LSI-Dataset will be publicly available at https://github.KD.LPR.com/.

Evidence of vertical transmission of fowl adenovirus 8b in ducks.

Fowl adenovirus mainly causes hydropericardium hepatitis syndrome (HHS), inclusion body hepatitis (IBH) and gizzard erosion (GE), etc. In 2015, the first outbreak of HHS was reported in broiler chickens in central China, followed by an outbreak in waterfowl. The first outbreak of HHS in broiler flocks in central China in 2015, followed by outbreaks in waterfowl, has severely restricted the healthy development of the poultry industry. During the investigation, fowl adenovirus was detected in ducklings from a total of seven hatcheries in Shandong, Inner Mongolia and Jiangsu provinces. In addition, the DNA of fowl adenovirus was detected in breeding ducks and their progeny. To test the hypothesis that FAdV can be transmitted vertically, sixty 250-day-old Cherry Valley breeder ducks were divided equally into three groups for experimental infection. FAdV-8b SDLY isolate (duck/Shandong/SDLY/2021, SDLY) preserved in our laboratory was injected intramuscularly into group A and inoculated orally into group B. FAdV-8b DNA was detected in the yolk membranes, embryos and allantoic fluid of duck embryos in the FAdV-infected group after inoculation. In addition, the FAdV-8b hexon gene isolated from yolk membranes, embryos, allantoic fluid and duck eggs was close to 100% nucleotide homology to the FAdV-8b hexon gene isolated from laying duck ovaries, indicating that fowl adenovirus can be transmitted vertically in ducks. These findings provide evidence for the possible vertical transmission of fowl adenovirus from breeder ducks to ducklings.

Deep Inference Networks for Reliable Vehicle Lateral Position Estimation in Congested Urban Environments.

Reliable estimation of vehicle lateral position plays an essential role in enhancing the safety of autonomous vehicles. However, it remains a challenging problem due to the frequently occurred road occlusion and the unreliability of employed reference objects (e.g., lane markings, curbs, etc.). Most existing works can only solve part of the problem, resulting in unsatisfactory performance. This paper proposes a novel deep inference network (DINet) to estimate vehicle lateral position, which can adequately address the challenges. DINet integrates three deep neural network (DNN)-based components in a human-like manner. A road area detection and occluding object segmentation (RADOOS) model focuses on detecting road areas and segmenting occluding objects on the road. A road area reconstruction (RAR) model tries to reconstruct the corrupted road area to a complete one as realistic as possible, by inferring missing road regions conditioned on the occluding objects segmented before. A lateral position estimator (LPE) model estimates the position from the reconstructed road area. To verify the effectiveness of DINet, road-test experiments were carried out in the scenarios with different degrees of occlusion. The experimental results demonstrate that DINet can obtain reliable and accurate (centimeter-level) lateral position even in severe road occlusion.