Pedestrian detection is the task of detecting pedestrians from a camera.
Further state-of-the-art results (e.g. on the KITTI dataset) can be found at 3D Object Detection.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates.
#17 best model for Person Re-Identification on DukeMTMC-reID
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection.
#9 best model for Face Detection on WIDER Face (Hard)
Like edges, corners, blobs and other feature detectors, the proposed detector scans for feature points all over the image, for which the convolution is naturally suited.
SOTA for Pedestrian Detection on Caltech (using extra training data)
Such "in-the-tail" data is notoriously hard to observe, making both training and testing difficult.
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
#2 best model for Pedestrian Detection on Caltech (using extra training data)
However, current single-stage detectors (e. g. SSD) have not presented competitive accuracy on common pedestrian detection benchmarks.
#3 best model for Pedestrian Detection on CityPersons
Then, the learned feature representations are transferred to a second deep network, which receives as input an RGB image and outputs the detection results.