A novel hardware-oriented ultra-high-speed object detection algorithm based on convolutional neural network
- PDF / 1,942,734 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 82 Downloads / 165 Views
ORIGINAL RESEARCH PAPER
A novel hardware‑oriented ultra‑high‑speed object detection algorithm based on convolutional neural network Jianquan Li1,2 · Xianlei Long1,2 · Shenhua Hu1,2 · Yiming Hu1,2 · Qingyi Gu1,2 · De Xu1,2 Received: 28 January 2019 / Accepted: 23 November 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract This paper describes a hardware-oriented two-stage algorithm that can be deployed in a resource-limited field-programmable gate array (FPGA) for fast-object detection and recognition with out external memory. The first stage is the bounding boxes proposal with a conventional object detection method, and the second is convolutional neural network (CNN)-based classification for accuracy improvement. Frequently accessing external memories significantly affects the execution efficiency of object classification. Unfortunately, the existing CNN models with a large number of parameters are difficult to deploy in FPGAs with limited on-chip memory resources. In this study, we designed a compact CNN model and performed the hardware-oriented quantization for parameters and intermediate results. As a result, CNN-based ultra-fast-object classification was realized with all parameters and intermediate results stored on chip. Several evaluations were performed to demonstrate the performance of the proposed algorithm. The object classification module consumes only 163.67 Kbits of on-chip memories for ten regions of interest (ROIs), this is suitable for low-end FPGA devices. In the aspect of accuracy, our method provides a correctness rate of 98.01% in open-source data set MNIST and over 96.5% in other three self-built data sets, which is distinctly better than conventional ultra-high-speed object detection algorithms. Keywords FPGA implementation · High-speed vision · Fast-object detection · Convolutional neural network
1 Introduction Object detection is a fundamental computer vision problem in which objects must be located and the category inside the regions of interest (ROIs) must be recognized. Various methods have been proposed for object detection and recognition; these methods are divided into two main categories. One is handcrafted feature-based methods, such as the Scale Invariant Feature Transform (SIFT) and Histogram of Oriented Gradients (HOG). The other is convolutional neural network (CNN)-based methods such as Region with CNN feature (R-CNN) and You Only Look Once (YOLO). Most of these algorithms perform high-accuracy object detection. However, processing speed is limited to 100 frames per second * Qingyi Gu [email protected] 1
The Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China
The School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China
2
(FPS) constrained by calculation power and algorithm complexity. However, in the fields of robotics and bioengineering, high-speed objects should be detected and recognized by intelligent sensors at more than 10
Data Loading...
