The algorithm of nighttime pedestrian detection in intelligent surveillance for renewable energy power stations

Abstract

Intelligent surveillance is an important management method for the construction and operation of power stations such as wind power and solar power. The identification and detection of equipment, facilities, personnel, and behaviors of personnel are the key technology for the ubiquitous electricity The Internet of Things. This paper proposes a video solution based on support vector machine and histogram of oriented gradient (HOG) methods for pedestrian safety problems that are common in night driving. First, a series of image preprocessing methods are used to optimize night images and detect lane lines. Second, an image is divided into intelligent regions to be adapted to different road environments. Finally, the HOG and support vector machine methods are used to optimize the pedestrian image on a Linux system, which reduces the number of false alarms in pedestrian detection and the workload of the pedestrian detection algorithm. The test results show that the system can successfully detect pedestrians at night. With image preprocessing optimization, the correct rate of nighttime pedestrian detection can be significantly improved, and the correct rate of detection can reach 92.4%. After the division area is optimized, the number of false alarms decreases significantly, and the average frame rate of the optimized video reaches 28 frames per second.

Building integrated renewable energy

“…Renewable energy can be used to power barrier-free intelligent surveillance systems. Peng et al. (2020a) develop algorithms to improve the accuracy and reduce the work load for night time pedestrian detection, which can improve the correct rate of detection to 92.4%, thus reducing the energy requirements of the power station.…”

Real and Pseudo Pedestrian Detection Method with CA-YOLOv5s Based on Stereo Image Fusion

“…Since these false positive samples have similar characteristics to pedestrians, they are always incorrectly detected as pedestrian by most pedestrian detection algorithms [ 19 ]. The incorrect detection of false positive samples, such as trash cans, traffic lights and trees has been solved through network improvement [ 20 , 21 , 22 ]. However, the incorrect detection of people printed on flat surfaces has not been well solved because printed people have almost exactly the same characteristics as pedestrians.…”