ABSTRACT
The core of robot visual servo is how to quickly and accurately recognize the image with the target features under the complex multi-constraint conditions. Mainly combines the characteristics of visual servo system for target detection, and based on the integrated network structure of target detection and feature extraction of YOLO training method, this paper proposes a method of matching the target position of the previous frame with the predicted position of the current frame obtained by Kalman filtering, which is used to locate the key point to judge whether there is a target in the predicted position. Five typical practical application examples are used to demonstrate the effectiveness of the proposed method in the detection efficiency as well as the success rate of image target features.
- Mahendru M, Dubey S K. Real-Time Object Detection with Audio Feedback using Yolo vs. Yolo_v3; proceedings of the 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), F,28-29 Jan. 2021, 2021 [C].Google ScholarCross Ref
- Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation; proceedings of the IEEE conference on computer vision and pattern recognition, F, 2015 [C].Google ScholarCross Ref
- Mcfadyen A, Jabeur M, Corke P. Image-Based Visual Servoing With Unknown Point Feature Correspondence [J]. IEEE Robotics and Automation Letters, 2017, 2(2): 601-607.Google ScholarCross Ref
- Li R, Hu J, Li S, Blind Detection of Communication Signals Based on Improved YOLO3; proceedings of the 2021 6th International Conference on Intelligent Computing and Signal Processing (ICSP), F 9-11 April 2021, 2021 [C].Google ScholarCross Ref
- Jin Punan. Vision-based Mobile Robot's Environment Perception[D], SHANDONG UNIVERSITY,2020.(in chinese)Google Scholar
- Shi Y, Qiao J, Song J, ROI Detection of Hand Bone Based on YOLO V3; proceedings of the 2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), F 28-30 June 2021, 2021 [C].Google ScholarCross Ref
- Nguyen D T, Nguyen T N, Kim H, A High-Throughput and Power-Efficient FPGA Implementation of YOLO CNN for Object Detection [J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2019, 27(8): 1861-1873.Google Scholar
- Szegedy C, Liu W, Jia Y, Going deeper with convolutions; proceedings of the Proceedings of the IEEE conference on computer vision and pattern recognition, F, 2015 [C].Google ScholarCross Ref
- Xu X, Xie M, Miao P, Perceptual-Aware Sketch Simplification Based on Integrated VGG Layers [J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(1): 178-189.Google ScholarDigital Library
- Fabijańska A, Gocławski J. The Segmentation of 3D Images Using the Random Walking Technique on a Randomly Created Image Adjacency Graph [J]. IEEE Transactions on Image Processing, 2015, 24(2): 524-537.Google ScholarDigital Library
- Jatla V, Pattichis M S, Arge C N. Image Processing Methods for Coronal Hole Segmentation, Matching, and Map Classification [J]. IEEE Transactions on Image Processing, 2020, 29: 1641-1653.Google ScholarCross Ref
Index Terms
- Accurate Spatial Positioning of Target Images in Visual Servo System under Multiple Constraints
Recommendations
Multiple feature points representation in target localization of wireless visual sensor networks
This paper discusses the target localization problem in wireless visual sensor networks. Additive noises and measurement errors will affect the accuracy of target localization when the visual nodes are equipped with low-resolution cameras. In the goal ...
Accurate Bluetooth Positioning Using Weighting and Large Number of Devices Measurements
In this paper it considers using the built-in Bluetooth in the cellphone as the positioning device; it is able from the measured received signal strength indication strength to locate the target or the cellphone position. From experimental measurements ...
Analysis of TDOA based radar target positioning in LOS and NLOS environments
We present the analysis of a radar target positioning technique in both Line-of-Sight LOS and Non-Line-of-Sight NLOS environments. A Time-Difference-of-Arrival TDOA method is investigated to find the target position and its positioning accuracy in terms ...
Comments