Enhanced Multi-Scale Object Detection Algorithm for Foggy Traffic Scenarios
Source abstract
Abstract
In foggy traffic scenarios, existing object detection algorithms face challenges such as low detection accuracy, poor robustness, occlusion, missed detections, and false detections. To address this issue, a multi-scale object... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Fire Detection and Safety Systems · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (36)
Show source-provided references
1. AOD-Net: All-in-one dehazing network
2. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
3. DSNet: Joint semantic learning for object detection in inclement weather conditions
4. Benchmarking single-image dehazing and beyond10.1109/TIP.2018.2867951 ↗
5. Rich feature hierarchies for accurate object detection and semantic segmentation
6. Fast R-CNN
7. Mask R-CNN
8. DAGL-Faster: Domain adaptive faster R-CNN for vehicle object detection in rainy and foggy weather conditions10.1016/j.displa.2023.102484 ↗
9. Domain adaptive faster R-CNN for object detection in the wild
10. Rethinking attentive object detection via neural attention learning10.1109/TIP.2023.3251693 ↗
11. You only look once: Unified, real-time object detection
12. SSD: Single shot multibox detector
13. Vehicle and pedestrian detection based on AOD-Net and SSD algorithm in hazy environment
14. Improved object detection of YOLOv4 in foggy conditions
15. Image-adaptive YOLO for object detection in adverse weather conditions
16. Multiscale domain adaptive YOLO for cross-domain object detection
17. Based on section local histogram equalization image enhancement algorithm
18. An image fusion dehazing algorithm based on dark channel prior and Retinex
19. BDPK: Bayesian dehazing using prior knowledge10.1109/TCSVT.2018.2869594 ↗
20. Contrast restoration of weather degraded images10.1109/TPAMI.2003.1201821 ↗
21. Single image haze removal using dark channel prior
22. DehazeNet: An end-to-end system for single image haze removal10.1109/TIP.2016.2598681 ↗
23. Light-DehazeNet: A novel lightweight CNN architecture for single image dehazing10.1109/TIP.2021.3116790 ↗
24. Rotate to attend: Convolutional triplet attention module
25. Diverse branch block: Building a convolution as an inception-like unit
26. Distance-IoU loss: Faster and better learning for bounding box regression
27. S. Ma and Y. Xu, “MPDIoU: A loss for efficient and accurate bounding box regression,” Jul. 2023, arXiv:2307.07662.
28. CBAM: Convolutional block attention module
29. Multi-attention network for compressed video referring object segmentation
30. Squeeze-and-excitation networks
31. J. Park, S. Woo, J. Y. Lee, and I. S. Kweon, “BAM: Bottleneck attention module,” Jul. 2018, arXiv:1807.06514.
32. NGCNet: On-local networks meet squeeze-excitation networks and beyond
33. The PASCAL visual object classes (VOC) challenge10.1007/s11263-009-0275-4 ↗
34. Ultralytics/yolov5: v5.0-YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations
35. DENet: Detection-driven enhancement network for object detection under adverse weather conditions
36. C. -Y. Wang, I. -H. Yeh, and H. -Y. M. Liao, “YOLOv9: Learning what you want to learn using programmable gradient information,” 2024, arXiv:2402.13616.10.1007/978-3-031-72751-1_1 ↗