Company News
A Sample Pre-mapping Method Enhancing Boosting for Object Detection
|
Haoyu Ren, Xiaopeng Hong, Cher-Keng Heng, Luhong Liang, Xilin Chen
International Conference on Pattern Recognition (ICPR) 2010, 2010.08
We propose a novel method to improve the training efficiency and accuracy of boosted classifiers for object detection. The key step of the proposed method is a sample pre-mapping on original space by referring to the selected `reference sample’ before feeding into weak classifiers. The reference sample corresponds to an approximation of the optimal separating hyper-plane in an implicit high dimensional space, so that the resulting classifier could achieve the performance similar to kernel method, while spending the computation cost of linear classifier in both training and detection. We employ two different non-linear mappings to verify the proposed method under boosting framework. Experimental results show that the proposed approach achieves performance comparable with the common used methods on public datasets in both pedestrian detection and car detection.
Related Posts
Panasonic R&D Center Singapore Achieves No. 1 Accuracy of Face Recognition on the IJB-C Dataset
Panasonic R&D Center Singapore achieved the Best Accuracy of Face Recognition on the IJB-C dataset under three different protocols, namely 1:1 mixed verification, 1:N mixed identification and 1:1 covariate verification.
Read morePanasonic R&D Center Singapore participated in TechInnovation 2017
Panasonic R&D Center Singapore had a presence at TechInnovation 2017, a technology-industry brokerage event organized by IPI Singapore at Sands Expo & Convention Centre on 19-20 September 2017, to exhibit 12 posters featuring technologies such as artificial intelligence, autonomous driving, data analytics, wireless communications, etc.
Read morePanasonic Auto Tracking Software Key AW-SF100/200 Powered by Panasonic R&D Center Singapore’s Face Recognition Module
Panasonic R&D Center Singapore’s Face Recognition module has been incorporated into the latest version of the Panasonic Auto Tracking Software…
Read morePaper accepted for publication in the special issue of the IEEE Transactions on Circuits and Systems for Video Technology
Teaming up with several world-renowned video experts, Panasonic R&D Center Singapore co-authored a paper titled “General Video Coding Technology in…
Read more
