Int J Performability Eng ›› 2018, Vol. 14 ›› Issue (11): 2702-2710.doi: 10.23940/ijpe.18.11.p16.27022710

Previous Articles     Next Articles

A Multi-Target Detection Algorithm for Infrared Image based on Retinex and LeNet5 Neural Network

Lijun Yuna, b, c, *, Tao Chena, Zaiqing Chena, b, and Kun Wanga   

  1. a School of Information, Yunnan Normal University, Kunming, 650500, China;
    b Yunnan Key Laboratory of Opto-electronic Information Technology, Kunming, 650500, China;
    c Key Laboratory of Educational Informatization for Nationalities Ministry of Education, Yunnan Normal University, Kunming, 650500, China
  • Submitted on ;
  • Contact: * E-mail address: yunlj@163.com
  • About author:Yun Lijun received his Ph.D. from Hebei University of Technology in 2006. He is currently the assistant dean of the School of Information at Yunnan Normal University. His main research interests include IoT and embedded systems.Chen Tao received his B.S. degree from Wuhan University in 2015. He is currently a Master's student at Yunnan Normal University. His main research interests include computer vision applications in detection and tracking.Chen Zaiqing received his M.S. degree from Yunnan University in 2008 and his Ph.D. from Yunnan Normal University in 2013. He is currently an associate professor in the School of Information at Yunnan Normal University. His research interests focus on 3D displays, human vision, and computer vision.Wang Kun received his bachelor's degree and Master's degree from Yunnan Normal University in 2008 and 2011, respectively. He is currently a Ph.D. student in communication engineering at Hohai University. His current research interests include computer vision applications in detection and tracking.

Abstract: Objectdetection in infrared video images is an important and challenging work. Due to low resolution, poor contrast, and low visual quality, target detection in infrared images is inefficient and prone to having higher false positive and lower precision rates. To improve detection efficiency, according to the characteristics of infrared images, we proposed a multi-target detection algorithm based on image enhancement and the LeNet5 deep neural network. In our method, we used the Retinex image enhance algorithm to protrude the edge contour and contrast, highlight the detailed features, and enhance the overall visibility of infrared images. In particular, the LeNet5 convolution neural network and CVC vehicle-assisted driving database were used to train the interesting target in the infrared image to generate the target data model, and the selective search algorithm was used to segment the candidate detect object regions in the image. The separated candidate regions were sent to the trained data model to classify the type and locate the position of objects in the image. The simulation results in CVC infrared image subset datasets show that our algorithm has higher detection speed and accuracy than the traditional HOG-based and LBP-based detection algorithms.

Key words: infrared image, Retinex, LeNet5 neural network, multi-target detection