改进Camshift算法的DSP硬件实现目标跟踪方法

王立和

doi:10.13718/j.cnki.xsxb.2018.11.011

西南师范大学学报(自然科学版)

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
	姓名不能为空！
邮箱
	邮箱不能为空！非法的邮箱地址。
手机号码
	电话不能为空！请输入有效手机号!
标题
	标题不能为空！
留言内容
	内容不能为空！
验证码
	验证码不能为空！验证码错误！

改进Camshift算法的DSP硬件实现目标跟踪方法

王立和. 改进Camshift算法的DSP硬件实现目标跟踪方法[J]. 西南师范大学学报(自然科学版), 2018, 43(11): 63-70. doi: 10.13718/j.cnki.xsxb.2018.11.011

引用本文:

王立和. 改进Camshift算法的DSP硬件实现目标跟踪方法[J]. 西南师范大学学报(自然科学版), 2018, 43(11): 63-70. doi: 10.13718/j.cnki.xsxb.2018.11.011

WANG Li-he. Target Tracking Method Based on DSP Hardware Improved Camshift Algorithm[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(11): 63-70. doi: 10.13718/j.cnki.xsxb.2018.11.011

Citation:

WANG Li-he. Target Tracking Method Based on DSP Hardware Improved Camshift Algorithm[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(11): 63-70. doi: 10.13718/j.cnki.xsxb.2018.11.011

改进Camshift算法的DSP硬件实现目标跟踪方法

王立和

重庆电子工程职业学院计算机学院, 重庆 401331

Target Tracking Method Based on DSP Hardware Improved Camshift Algorithm

WANG Li-he

Department of Computer, Chongqing College of Electronic Engineering, Chongqing 401331, China

摘要: 针对Camshift算法只对前一帧预测而导致的目标像素脱靶现象，以及目标像素在帧间位移较大的问题，本文提出一种改进Camshift算法的目标跟踪方法.该算法将加权背景直方图和贪心算法融入Camshift算法，利用贪心算法对前两帧图像信息进行处理，预测出目标在当前帧图像中的位置，再根据目标颜色概率，用Camshift算法找到目标的真实位置，最后在TMS320DM642（数字媒体应用的定点DSP）上对该文算法进行硬件系统的实现，并使用EDMA （增强型直接内存访问）方式和Cache技术对系统进行优化.实验结果表明，与传统Camshift算法相比，该文方法在背景与目标相近的情况下跟踪效果更佳，具有很好的鲁棒性和稳定性，适用于复杂环境下的目标跟踪.在系统实现上，优化后的系统平均帧率提升在3帧/s以上，增强了算法的速度.
- 改进Camshift算法 /
- 自适应背景 /
- 目标跟踪 /
- 贪心算法 /
- TMS320DM642
Abstract: In order to solve the problem that the target pixel is lost caused by the prediction of the previous frame of the Camshift algorithm and the target pixel is greatly shifted between frames, a target tracking method based on improved Camshift algorithm is proposed in this paper. The algorithm combines the weighted background histogram and the greedy algorithm into Camshift algorithm, and uses the greedy algorithm to process the image information of the first two frames to predict the position of the target in the current frame image. Then the Camshift algorithm is used to find out the target's reality according to the target color probability Location. Finally, the hardware system is implemented on the TMS320DM642. Then using EDMA and Cache technology optimize the system. Compared with the traditional Camshift algorithm, Experimental results show that the proposed method has better tracking performance and better robustness and stability under the condition of similar background and target, which is suitable for the target tracking in complex environment. In the system implementation, the average system frame rate of the optimized system is increased by more than 3 frames/second, which increases the speed of the algorithm.
- improved camshift algorithm /
- background weighted histogram /
- target tracking /
- greedy algorithm /
- TMS320DM642 .

[1]	王明波. 运动目标跟踪方法综述[J]. 计算机与数字工程,2016,44(11):2164-2167,2208.
[2]	谭艳,王宇俊. 一种结合背景差分的改进CamShift目标跟踪方法[J]. 西南师范大学学报(自然科学版),2016,41(9):120-125.
[3]	孔军,蒋敏,唐晓微,等. 一种面向高斯差分图的压缩感知目标跟踪算法[J]. 红外与毫米波学报,2015,34(1):100-105.
[4]	董安国,梁苗苗. 基于灰度相关性的裂缝检测算法[J].计算机应用研究,2013,30(10):3121-3123.
[5]	KASS M,WITKINM A,TERZOPOULOS D. Snakes:Active Contour Models[J]. International Journal on Computer Vision, 1998, 1(4):321-331.
[6]	黄园刚,桑楠,郝宗波,等. 改进CamShift算法的眼动跟踪方法[J]. 计算机应用研究,2014,31(4):88-92.
[7]	OKAMOTO S,POULADI M A,TALANTOVA M,et al. Balance Between Synaptic Versus Extrasynaptic NMDA Receptor Activity Influences Inclusions and Neurotoxicity of Mutant Huntingtin[J]. Nature medicine,2012,15(12):1407-1413.
[8]	李涛,黄仁杰,李冬梅,等. 基于线性拟合的多运动目标跟踪算法[J]. 西南师范大学学报(自然科学版),2015, 40(5):44-49.
[9]	初红霞,谢忠玉,王希凤,等. 基于改进粒子滤波的多目标跟踪算法研究[J]. 计算机工程与设计,2014,35(6):2142-2146.
[10]	WANG Q,WARD R K. Fast Image/Video Contrast Enhancement Based on Weighted Thresholded Histogram Equalization[J]. Consumer Electronics,IEEE Transactions on,2012,53(2):757-764.
[11]	支祖利,高智勇,赵妮娜,等. 基于ABCshift结合Kalman滤波的目标跟踪算法[J]. 计算机应用与软件,2014,31(2):226-229.

计量

文章访问数: 756
HTML全文浏览数: 511
PDF下载数: 119
施引文献: 0

改进Camshift算法的DSP硬件实现目标跟踪方法

王立和

重庆电子工程职业学院计算机学院, 重庆 401331

收稿日期: 2018-01-02

关键词:

摘要: 针对Camshift算法只对前一帧预测而导致的目标像素脱靶现象，以及目标像素在帧间位移较大的问题，本文提出一种改进Camshift算法的目标跟踪方法.该算法将加权背景直方图和贪心算法融入Camshift算法，利用贪心算法对前两帧图像信息进行处理，预测出目标在当前帧图像中的位置，再根据目标颜色概率，用Camshift算法找到目标的真实位置，最后在TMS320DM642（数字媒体应用的定点DSP）上对该文算法进行硬件系统的实现，并使用EDMA （增强型直接内存访问）方式和Cache技术对系统进行优化.实验结果表明，与传统Camshift算法相比，该文方法在背景与目标相近的情况下跟踪效果更佳，具有很好的鲁棒性和稳定性，适用于复杂环境下的目标跟踪.在系统实现上，优化后的系统平均帧率提升在3帧/s以上，增强了算法的速度.

English Abstract

Target Tracking Method Based on DSP Hardware Improved Camshift Algorithm

重庆电子工程职业学院计算机学院, 重庆 401331

Received Date: 2018-01-02

Keywords:

Abstract: In order to solve the problem that the target pixel is lost caused by the prediction of the previous frame of the Camshift algorithm and the target pixel is greatly shifted between frames, a target tracking method based on improved Camshift algorithm is proposed in this paper. The algorithm combines the weighted background histogram and the greedy algorithm into Camshift algorithm, and uses the greedy algorithm to process the image information of the first two frames to predict the position of the target in the current frame image. Then the Camshift algorithm is used to find out the target's reality according to the target color probability Location. Finally, the hardware system is implemented on the TMS320DM642. Then using EDMA and Cache technology optimize the system. Compared with the traditional Camshift algorithm, Experimental results show that the proposed method has better tracking performance and better robustness and stability under the condition of similar background and target, which is suitable for the target tracking in complex environment. In the system implementation, the average system frame rate of the optimized system is increased by more than 3 frames/second, which increases the speed of the algorithm.