Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors

We propose methods of addressing two critical issues of pedestrian detection: (i) occlusion of target objects as false negative failure, and (ii) confusion with hard negative examples like vertical structures as false positive failure. Our solutions to these two problems are general and flexible enough to be applicable to any single-stage detection models... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Global Average Pooling
Pooling Operations
Batch Normalization
Normalization
Max Pooling
Pooling Operations
Softmax
Output Functions
Convolution
Convolutions
Darknet-19
Convolutional Neural Networks
Non Maximum Suppression
Proposal Filtering
1x1 Convolution
Convolutions
SSD
Object Detection Models
YOLOv2
Object Detection Models