Deep Poselets for Human Detection
Abstract
We address the problem of detecting people in natural scenes using a part approach based on poselets. We propose a bootstrapping method that allows us to collect millions of weakly labeled examples for each poselet type. We use these examples to train a Convolutional Neural Net to discriminate different poselet types and separate them from the background class. We then use the trained CNN as a way to represent poselet patches with a Pose Discriminative Feature (PDF) vector -- a compact 256-dimensional feature vector that is effective at discriminating pose from appearance. We train the poselet model on top of PDF features and combine them with object-level CNNs for detection and bounding box prediction. The resulting model leads to state-of-the-art performance for human detection on the PASCAL datasets.
- Publication:
-
arXiv e-prints
- Pub Date:
- July 2014
- DOI:
- 10.48550/arXiv.1407.0717
- arXiv:
- arXiv:1407.0717
- Bibcode:
- 2014arXiv1407.0717B
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition