Towards Real-Time Object Detection on Embedded Systems
By Huizi Mao, Song Yao, Tianqi Tang, Boxun Li, Jun Yao, Yu Wang. 2018
85 citations recorded by the source corpus.
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<inline-formula><tex-math notation="LaTeX">$+$</tex-math><alternatives> <inline-graphic xlink:href="mao-ieq1-2593643.gif"/></alternatives></inline-formula>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<inline-formula><tex-math notation="LaTeX">$\cdot$ </tex-math><alternatives><inline-graphic xlink:href="mao-ieq2-2593643.gif"/></alternatives></inline-formula>h) on the embedded Jetson TK1 CPU<inline-formula><tex-math notation="LaTeX">$+$</tex-math><alternatives> <inline-graphic xlink:href="mao-ieq3-2593643.gif"/></alternatives></inline-formula>GPU platform.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
Citations in the corpus
- Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “[58] also used Fast R-CNN for embedded platforms reporting a run time of 1.”
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019, unknown): “Applying various convolutional filters, CNN models can capture the high-level representation of the input data, making it most popular for computer vision tasks, e.g., image classification (e.g., AlexNet [18], VGG network [19], ResNet [20], and MobileNet [21]) and object detection (e.g., Fast R-CNN ”