Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians
By Jialian Wu, Chunluan Zhou, Ming Yang, Qian Zhang, Yuan Li, Junsong Yuan. 2020
63 citations recorded by the source corpus.
State-of-the-art pedestrian detectors have performed promisingly on non-occluded pedestrians, yet they are still confronted by heavy occlusions. Although many previous works have attempted to alleviate the pedestrian occlusion issue, most of them rest on still images. In this paper, we exploit the local temporal context of pedestrians in videos and propose a tube feature aggregation network (TFAN) aiming at enhancing pedestrian detectors against severe occlusions. Specifically, for an occluded pedestrian in the current frame, we iteratively search for its relevant counterparts along temporal axis to form a tube. Then, features from the tube are aggregated according to an adaptive weight to enhance the feature representations of the occluded pedestrian. Furthermore, we devise a temporally discriminative embedding module (TDEM) and a part-based relation module (PRM), respectively, which adapts our approach to better handle tube drifting and heavy occlusions. Extensive experiments are conducted on three datasets, Caltech, NightOwls and KAIST, showing that our proposed method is significantly effective for heavily occluded pedestrian detection. Moreover, we achieve the state-of-the-art performance on the Caltech and NightOwls datasets.
Subfields: Automotive Engineering, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Automotive Engineering
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ling Shao
- Fahad Shahbaz Khan
- Ming-Hsuan Yang
- Dacheng Tao
- Alan L. Yuille
- Philip H. S. Torr
- Xiaogang Wang
Citations in the corpus
- Track to Detect and Segment: An Online Multi-Object Tracker (2021, methodology): “5]⊤ Current Center Previous Center O14,33 C = [50, 118]⊤ (Prediction) (Ground Truth) (Ground Truth) (Ground Truth) (312, 864)”
- SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (2020, background): “et [48], our single-stage approach achieves favourable performance while operating at real-time (30 fps). 2 Related Work Deep learning has achieved great success in a variety of computer vision tasks [20,12,43,35,45,44,25,24,53,52]. Existing instance segmentation methods either follow bottom-up [1,2”
- Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (2020, background): “ries, respectively. 2 RELATED WORK ObjectDetectionandInstanceSegmentation.Objectdetection, which plays an important role in various vision applications, has been actively investigated in past decades [4, 6, 7, 23, 32, 34, 40, 41]. With deep learning, two mainstream frameworks, i.e., single-stage det”
- Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge (2021, background): “[36] aggregates the temporal context to enhance the feature representations.”