A foreground detection algorithm based on improved three-frame difference method and improved Gaussian mixed model

2019 ◽  
Author(s):  
Min Shang ◽  
Shan Zeng ◽  
Liang Jiang
Keyword(s):  
Difference Method ◽  
Mixed Model ◽  
Detection Algorithm ◽  
Foreground Detection ◽  
Frame Difference

A Moving Object Detection Algorithm Based on ORB under Dynamic Scene

2014 ◽  
Vol 602-605 ◽  
pp. 1638-1641 ◽  
Author(s):  
Wen Hao Luo
Keyword(s):  
Object Detection ◽  
Difference Method ◽  
High Speed ◽  
Detection Algorithm ◽  
Moving Object Detection ◽  
Moving Object ◽  
Transformation Model ◽  
Dynamic Scene ◽  
Frame Difference ◽  
Inter Frame

In this thesis, a moving object detection algorithm under dynamic scene is proposed, which is based on ORB feature. Firstly, we extract feature points and match them by using ORB. We then obtain global motion compensation image by parameters of transformation matrix based on the RANSAC method. Finally, we use the inter-frame difference method to achieve the detection of moving targets. The high speed and accuracy of ORB feature point matching method, as well as the effectiveness of the RANSAC method for removing outliers ensure accurate calculation of parameters of affine transformation model. Combined with inter-frame difference method, foreground objects can be detected entirely. Experiment results show that the algorithm can accurately detect moving objects, and to some extent, it can solve the issue of real-time detection.

scholarly journals Deep Learning-Driven Gaussian Modeling and Improved Motion Detection Algorithm of the Three-Frame Difference Method

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Dingchao Zheng ◽  
Yangzhi Zhang ◽  
Zhijian Xiao
Keyword(s):  
Deep Learning ◽  
Motion Detection ◽  
Adaptive Learning ◽  
Difference Method ◽  
Gaussian Model ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Frame Difference ◽  
Gaussian Modeling ◽  
Difference Calculation

To enhance the effect of motion detection, a Gaussian modeling algorithm is proposed to fix holes and breaks caused by the conventional frame difference method. The proposed algorithm uses an improved three-frame difference method. A three-frame image sequence with one frame interval is selected for pairwise difference calculation. The logical “OR” operation is used to achieve fast motion detection and to reduce voids and fractures. The Gaussian algorithm establishes an adaptive learning model to make the size and contour of the motion detection more accurate. The motion extracted by the improved three-frame difference method and Gaussian model is logically summed to obtain the final motion foreground picture. Moreover, a moving target detection method, based on the U-Net deep learning network, is proposed to reduce the dependency of deep learning on the number of training datasets. It helps the algorithm to train models on small datasets. Next, it calculates the ratio of the number of positive and negative samples in the dataset and uses the reciprocal of the ratio as the sample weight to deal with the imbalance of positive and negative samples. Finally, a threshold is set to predict the results for obtaining the moving object detection accuracy. Experimental results show that the algorithm can suppress the generation and rupture of holes and reduce the noise. Also, it can quickly and accurately detect movement to meet the design requirements.

scholarly journals Visual Sequence Algorithm for Moving Object Tracking and Detection in Images

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Renzheng Xue ◽  
Ming Liu ◽  
Xiaokun Yu
Keyword(s):  
Target Detection ◽  
Difference Method ◽  
Moving Objects ◽  
Target Location ◽  
Mean Shift ◽  
Detection Algorithm ◽  
Moving Target ◽  
Size Change ◽  
Detection And Tracking ◽  
Frame Difference

Objective. The effects of different algorithms on detecting and tracking moving objects in images based on computer vision technology are studied, and the best algorithm scheme is confirmed. Methods. An automatic moving target detection and tracking algorithm based on the improved frame difference method and mean-shift was proposed to test whether the improved algorithm has improved the detection and tracking effect of moving targets. The algorithm improves the traditional three-frame difference method and introduces a single Gaussian background model to participate in target detection. The improved frame difference method is used to detect the target, and the position window and center of the target are determined. Combined with the mean-shift algorithm, it is determined whether the template needs to be updated according to whether it exceeds the set threshold so that the algorithm can automatically track the moving target. Results. The position and size of the search window change as the target location and size change. The Bhattacharyya similarity measure ρ (y) exceeds the threshold r, and the target detection algorithm is successfully restarted. Conclusion. The algorithm for automatic detection and tracking of moving objects based on the improved frame difference method and mean-shift is fast and has high accuracy.

scholarly journals Volleyball Action Extraction and Dynamic Recognition Based on Gait Tactile Sensor

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Limin Qi
Keyword(s):  
Human Body ◽  
Difference Method ◽  
Body Position ◽  
Capture Rate ◽  
Detection Algorithm ◽  
Human Motion ◽  
Position Estimation ◽  
Test Method ◽  
Frame Difference ◽  
Background Segmentation

At present, the industry research of volleyball technology is relatively in-depth, and the analysis of the muscle strength characteristics and coordination of the jumping ball is less, which is not conducive to the control of technical movements. This study used a wireless portable surface EMG tester (16 lines) to analyze the EMG of the main muscle groups in athletes’ volleyball and conducted a video synchronization test method to find the position of the human body. Therefore, a background-based frame difference method is proposed to detect the position and obtain the precise position of the human body. Experiments show that the background-based three-frame difference method effectively eliminates the “hole” effect of the original three-frame difference method and provides an accurate and complete framework for identifying the human body. Adjust the recognition frame according to the proportion of the human body in the image, and use the predefined parameters of the severe frame to perform forward/volleyball background segmentation. The novelty of this document lies in the completion of the complete human body placement of the above three tasks, precapture/background segmentation, and an improved human body position estimation algorithm to extract the human body pose from the video. First, locate the human body in each frame of the video, and then, perform the process of estimating the position of the graphic model based on the color and texture of the unit. After recognizing the gesture of each image in the video, the recognition result will be displayed. Experiments show that after detecting the position of the human body, the predefined frame setting process of the tomb is carried out in two steps, which improves the automation of the human body image detection algorithm, effectively extracts the human motion video, and increases the motion capture rate by more than 30%, to provide a useful reference for the improvement of college volleyball players’ movement skills and training competitions.

Vehicle Detection Method under Night Circumstance

2013 ◽  
Vol 380-384 ◽  
pp. 3870-3873 ◽  
Author(s):  
Lin Guo ◽  
Xiang Hui Shen
Keyword(s):  
Difference Method ◽  
Moving Objects ◽  
Detection Method ◽  
Vehicle Detection ◽  
Detection Algorithm ◽  
Intelligent Vehicle ◽  
Urban Street ◽  
Light Interference ◽  
Frame Difference

In intelligent vehicle detection, vehicle detection at night especially detection in the condition of urban street always remains a problem. This paper proposes an effective vehicle detection algorithm. Firstly it extracts effective vehicle edge by the method of embossment which eliminates light interference. Then we detect the vehicle moving area by frame difference method and calculate the threshold by OTSU algorithm. Finally the noise points are removed by erosion and expansion. This method can better extract the moving objects.

Adaptive Moving Vehicle Detection Algorithm Based on Hybrid Background Subtraction and Frame Difference

2014 ◽  
Vol 644-650 ◽  
pp. 930-933 ◽  
Author(s):  
Yan Li Luo ◽  
Han Lin Wan ◽  
Li Xia Xue ◽  
Qing Bin Gao
Keyword(s):  
Background Subtraction ◽  
Vehicle Detection ◽  
Detection Algorithm ◽  
Target Image ◽  
Moving Vehicle ◽  
Frame Difference ◽  
Video Frequency ◽  
Background Difference ◽  
Moving Vehicle Detection ◽  
Initial Target

This paper proposes an adaptive moving vehicle detection algorithm based on hybrid background subtraction and frame difference. The background image of continuous video frequency is reconstructed by calculating the maximun probability grayscale using grey histogram; Moving regions is gained by frame defference, the initial target image is obtained by background difference method,moving regions image and initial target image AND,XOR and OR operations to get the vehicle moving target images. Experimental results show that the algorithm can response timely to the actual scene changes and improve the quality of moving vehicle detection.

Sign in / Sign up

Export Citation Format

Share Document