Abstract
Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The interaction among these components is not yet well explored. This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four components into a joint deep learning framework and propose a new deep network architecture. By establishing automatic, mutual interaction among components, the deep model achieves a 9% reduction in the average miss rate compared with the current best-performing pedestrian detection approaches on the largest Caltech benchmark dataset.
Keywords
Pedestrian detectionComputer scienceDeep learningBenchmark (surveying)Artificial intelligenceJoint (building)PedestrianFeature extractionMachine learningPattern recognition (psychology)Data miningEngineering
Affiliated Institutions
Related Publications
Object Detection With Deep Learning: A Review
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection ...
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether...
Learning Hierarchical Features for Scene Labeling
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network traine...
Publication Info
- Year
- 2013
- Type
- article
- Citations
- 681
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
681
OpenAlex
Cite This
Wanli Ouyang,
Xiaogang Wang
(2013).
Joint Deep Learning for Pedestrian Detection.
.
https://doi.org/10.1109/iccv.2013.257
Identifiers
- DOI
- 10.1109/iccv.2013.257