Part-Aware Region Proposal for Vehicle Detection in High Occlusion Environment

Zhang, Wei Wei; Zheng, Yaocheng; Gao, Qiaoming; Mi, Zeyang

doi:10.1109/access.2019.2929432

Cited by 25 publications

(20 citation statements)

References 52 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the performance in fast and timevariant flow-field environments should be improved. The studies by Li et al 43 , Kwok and Martínez 44 and Zhang Weiwei et al 48 could serve as a reference to resolve the issues that may be encountered in the future.…”

Section: Discussionmentioning

confidence: 99%

Adaptive agent tracking approach for oil contamination in water environments

Huang

Chen

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The online monitoring of water environments is urgently needed. A feasible and effective approach is the use of agents. Water environments, similar to other real-world environments, present many changing and unpredictable situations. To ensure flexibility in such an environment, agents should be prepared to deal with various situations. In this study, we focused on an adaptive agent tracking approach for oil contamination. An integrated tracking framework, which is used to track the moving contour of oil pollution via a system comprising multiple unmanned surface vehicles, is proposed. The zigzag, unmanned underwater vehicle-gas, cloverleaf trajectory and curvature-weighted deployment algorithm methods are employed with consideration of their suitability to our approach. A cyclic particle swarm optimisation–Kalman method is also proposed. The possible position of moving vertices is predicted by the Kalman filter, and an objective search region is generated around the centre position. Moreover, particle swarm optimisation is performed to search for the best target position in this region. This particle swarm optimisation–Kalman method is circle operated to compensate for the deficiency of a few agents. To evaluate the approach, we conduct usability and performance simulations.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive agent tracking approach for oil contamination in water environments

Huang

Chen

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…At present, most researches on the recognition of occluded images mainly focus on large scale traditional objects of visible images, such as pedestrian detection [17], faces recognition [18], cars [19] and other occluded objects detection. In [17], a model based on Deformable Part Network (DPN) was proposed, which has the ability of reasoning and can predict the occluded parts.…”

Section: Occlusion Detectionmentioning

confidence: 99%

“…Firstly, the cascade classifier is applied to identify the eyes and mouth of a human face; then, the physical feature relationship between the eyes and mouth of a person and the face is used to identify and detect the entire masked face. In the context of urban autonomous driving system, Only useful for objects of large scales in simple background [1], [3][4][5], [24] Feature fusion+ attention mechanism Extract features of very small objects(2×2 pixels) Only useful for objects in simple background such as sky and sea [2], [6] Density map Detect the small and high density objects Not useful for single object detection [16] Extra information Has the ability of reasoning and predict the occluded parts Detection on traditional visible datasets [17][18][19] Ours (secondary transfer learning + HNEM)…”

Section: Occlusion Detectionmentioning

confidence: 99%

“…Decrease the impact of complex backgrounds and mitigate the lack of infrared datasets vehicles are blocked due to buildings, dynamic changes and limited perspective. In [19], Faster-RCNN network and the Part-Aware Region Proposal Network were used to perceive the partial or global visual information of a vehicle. By extracting and encoding matching the global and local information of a vehicle, the two feature frames were integrated, so that the model could reduce the influence caused by occlusion.…”

Section: Occlusion Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Weak and Occluded Vehicle Detection in Complex Infrared Environment Based on Improved YOLOv4

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Infrared small target detection is still a challenge in the field of object detection. At present, although there are many related research achievements, it surely needs further improvement. This paper introduced a new application of severely occluded vehicle detection in the complex wild background of weak infrared camera aerial images, in which more than 50% area of the vehicles are occluded. We used YOLOv4 as the detection model. By applying secondary transfer learning from visible dataset to infrared dataset, the model could gain a good average precision (AP). Firstly, we trained the model in the UCAS_AOD visible dataset, then, we transferred it to the VIVID visible dataset, finally we transferred the model to the VIVID infrared dataset for a second training. Meanwhile, added the hard negative example mining block to the YOLOv4 model, which could depress the disturbance of complex background thus further decrease the false detecting rate. Through experiments the average precision improved from90.34% to 91.92%, the F1 score improved from 87.5% to 87.98%, which demonstrated that the proposed algorithm generated satisfactory and competitive vehicle detection results. INDEX TERMS Infrared aerial image, occlusion, vehicle detection, hard negative example mining, YOLOv4.

show abstract

“…e experimental results showed that the proposed algorithm significantly improved the vehicle detection accuracy at different detection difficulty levels compared to the original YOLOv3 algorithm, especially for the vehicles with severe occlusion. In [25], the authors presented a two-stage detector based on Faster R-CNN for high-occluded vehicle detection. e partaware RPN is proposed to replace the original RPN at the first stage of the Faster R-CNN module, and the part-aware NMS is proposed to refine final results.…”

Section: Theoretical Basismentioning

confidence: 99%

Improving Faster R‐CNN Framework for Fast Vehicle Detection

Nguyen

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Vision-based vehicle detection plays an important role in intelligent transportation systems. With the fast development of deep convolutional neural networks (CNNs), vision-based vehicle detection approaches have achieved significant improvements compared to traditional approaches. However, due to large vehicle scale variation, heavy occlusion, or truncation of the vehicle in an image, recent deep CNN-based object detectors still showed a limited performance. This paper proposes an improved framework based on Faster R-CNN for fast vehicle detection. Firstly, MobileNet architecture is adopted to build the base convolution layer in Faster R-CNN. Then, NMS algorithm after the region proposal network in the original Faster R-CNN is replaced by the soft-NMS algorithm to solve the issue of duplicate proposals. Next, context-aware RoI pooling layer is adopted to adjust the proposals to the specified size without sacrificing important contextual information. Finally, the structure of depthwise separable convolution in MobileNet architecture is adopted to build the classifier at the final stage of the Faster R-CNN framework to classify proposals and adjust the bounding box for each of the detected vehicle. Experimental results on the KITTI vehicle dataset and LSVH dataset show that the proposed approach achieved better performance compared to original Faster R-CNN in both detection accuracy and inference time. More specific, the performance of the proposed method is improved comparing with the original Faster R-CNN framework by 4% on the KITTI test set and 24.5% on the LSVH test set.

show abstract

Part-Aware Region Proposal for Vehicle Detection in High Occlusion Environment

Cited by 25 publications

References 52 publications

Adaptive agent tracking approach for oil contamination in water environments

Adaptive agent tracking approach for oil contamination in water environments

Weak and Occluded Vehicle Detection in Complex Infrared Environment Based on Improved YOLOv4

Improving Faster R‐CNN Framework for Fast Vehicle Detection

Contact Info

Product

Resources

About