Towards Real-Time Object Detection on Embedded Systems
- 15 August 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. 6 (3), 417-431
- https://doi.org/10.1109/tetc.2016.2593643
Abstract
Convolutional neural network (CNN) based methods have achieved great success in image classification and object detection tasks. However, unlike the image classification task, object detection is much more computation-intensive and energy-consuming since a large number of possible object proposals need to be evaluated. Consequently, it is difficult for object detection methods to be integrated into embedded systems with limited computing resources and energy supply. In this paper, we propose a pipelined object detection implementation on the embedded platform. We present a comprehensive analysis of state-of-the-art object detection algorithms and select Fast R-CNN as a possible solution. Additional modifications on the Fast R-CNN method are made to fit the specific platform and achieve trade-off between speed and accuracy on embedded systems. Finally, a multi-stage pipelined implementation on the embedded CPU+GPU platform with duplicated module-parallelism is proposed to make full use of the limited computation resources. The proposed system is highly energy-efficient and close to real-time performance. In the first Low-Power Image Recognition Challenge (LPIRC), our system achieved the best result with mAP/Energy of 1.818e-2/ (W.h) on the embedded Jetson TK1 CPU+GPU platform.Keywords
Funding Information
- 973 Project (2013CB329000)
- National Natural Science Foundation of China (61373026)
- Brain Inspired Computing Research, Tsinghua university (20141080934)
- Tsinghua University Initiative Scientific Research Program
- Beijing Municipal Institutions
- Huawei Technologies
This publication has 27 references indexed in Scilit:
- What Makes for Effective Detection Proposals?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- The Pascal Visual Object Classes Challenge: A RetrospectiveInternational Journal of Computer Vision, 2014
- Integrated CPU-GPU Power Management for 3D Mobile GamesPublished by Association for Computing Machinery (ACM) ,2014
- DianNaoACM SIGPLAN Notices, 2014
- Performance Evaluation and Energy Efficiency of High-Density HPC Platforms Based on Intel, AMD and ARM ProcessorsLecture Notes in Computer Science, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989