A sparse deep feature representation for object detection from wearable cameras

Quanfu Fan, Chun Fu Chen, Gwo Giun Lee

研究成果: Conference contribution

2 引文 斯高帕斯(Scopus)

摘要

We propose a novel sparse feature representation for the faster RCNN framework and apply it for object detection from wearable cameras. Two main ideas, sparse convolution and sparse ROI pooling, are developed to reduce model complexity as well as computational cost. Sparse convolution approximates a full kernel by skipping weights in the kernel while sparse ROI pooling performs feature dimensionality reduction on the ROI pooling layer by skipping odd-indexed or even-indexed features. We demonstrate the effectiveness of our approach on two challenging body camera datasets including realistic police-generated clips. Our approach achieves a significant reduction of model size by a factor of over 10× as well as a computational speedup of about 2×, yet without compromising much detection accuracy compared to a VGG16-based baseline detector.

原文English
主出版物標題British Machine Vision Conference 2017, BMVC 2017
發行者BMVA Press
ISBN(電子)190172560X, 9781901725605
出版狀態Published - 2017 1月 1
事件28th British Machine Vision Conference, BMVC 2017 - London, United Kingdom
持續時間: 2017 9月 42017 9月 7

出版系列

名字British Machine Vision Conference 2017, BMVC 2017

Conference

Conference28th British Machine Vision Conference, BMVC 2017
國家/地區United Kingdom
城市London
期間17-09-0417-09-07

All Science Journal Classification (ASJC) codes

  • 電腦視覺和模式識別

指紋

深入研究「A sparse deep feature representation for object detection from wearable cameras」主題。共同形成了獨特的指紋。

引用此