ABSTRACT
Along with urbanization and the growth of the number of high-rise buildings, incidents of damage to personal property caused by objects thrown from high-rise buildings have increased in recent years. This paper designs a sensing method for the detection of objects thrown from high-rise buildings based on a binocular stereo vision sensor. The sensor is based on a binocular camera that acquires the 3D coordinates of a falling object after Camera Calibration, Rectification of Pixel Pairs and Extraction of Feature Point and Feature Points Searching & Matching. Feature Points Searching & Matching is one of the steps that implements Harris corner detection and ORB algorithm to accurately identify object feature points. This improves the recognition accuracy of thrown objects and also helps to determine the source of falling objects to get their precise floor height and the responsible party, thereby reducing falling object incidents and providing a reference for future development and application of binocular stereo vision.
- CAO Bo, “The Legitimate Foundation and Systematic Interpretation of the Criminal Regulation of Dropping Objects,” Hebei Law Science, vol.39, no.02, pp.157-173, 2021.Google Scholar
- Zhang Yu, Huang Bangjin, Cai Yurun, “Intelligent Monitoring Sys- tem for Dumps of High-rise Buildings Based on Ultrasonic and Cloud of Things Technology,” Mechanical Electrical Engineering Techno-logy, vol.49, no.09, pp.105-106+119, 2020.Google Scholar
- Wang Wenjie, Mu Yeshuai, Lan Peng, “Accurate High-altitude Throw Out-point Locator,” Scientific and Technological Innovation, no.02 ,pp.1-4,2022.Google Scholar
- ZHU Xiaoqin. “Design of Scene Monitoring and Recognition Sys- tem,” Applications, vol.38, no.11, pp.192-193, 2021.Google Scholar
- Misganu Debella-Gilo, Andreas Ka¨a¨b, “Sub-pixel precision image matching for measuring surface displacements on mass movements using normalized cross-correlation,” Remote Sensing of Environment, vol.115, no.01, pp.130-142, 2011Google ScholarCross Ref
- R. Tsai, “A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses,” in IEEE Journal on Robotics and Automation, vol. 3, no. 4, pp. 323-344, August 1987.Google ScholarCross Ref
- A. Quddus and M. M. Fahmy, ”An improved wavelet-based corner detection technique,” 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258), 1999, pp. 3213-3216 vol.6.Google ScholarDigital Library
- E. Rublee, V. Rabaud, K. Konolige and G. Bradski, ”ORB: An efficient alternative to SIFT or SURF,” 2011 International Conference on Computer Vision, 2011, pp. 2564-2571.Google ScholarDigital Library
- DENG Zhi-huan, DENG Zu-pei.“Measurement Exploration of Altitude Throwing Monitoring System Design,” Guangzhou Architecture, vol.41, no.05, pp.16-20, 2013Google Scholar
Index Terms
- Dropped Object Detection System Design Based on Binocular Stereo Vision Sensor
Recommendations
Binocular Spherical Stereo
A fish-eye camera has a wide field of view (FOV), and the realization of a binocular fish-eye stereo for sensing the surrounding 3-D information of the environment around a vehicle is useful for safe driving. However, since a fish-eye camera may have a ...
Multi-object detection and tracking by stereo vision
This paper presents a new stereo vision-based model for multi-object detection and tracking in surveillance systems. Unlike most existing monocular camera-based systems, a stereo vision system is constructed in our model to overcome the problems of ...
Catadioptric Stereo Using Planar Mirrors
By using mirror reflections of a scene, stereo images can be captured with a single camera (catadioptric stereo). In addition to simplifying data acquisition single camera stereo provides both geometric and radiometric advantages over traditional two ...
Comments