Fusion of Background Subtraction and Frame Difference in HSV Space for Multi-Object Detection

2013 ◽  
Vol 380-384 ◽  
pp. 3895-3899
Author(s):  
Ya Ne Wen ◽  
Hong Song Li ◽  
Hao Zhou ◽  
Li Ping Tang ◽  
Jun Qi She
Keyword(s):  
Difference Method ◽  
Background Subtraction ◽  
Gaussian Mixture ◽  
Test Results ◽  
Subtraction Method ◽  
False Detection ◽  
Strong Light ◽  
Fusion Frame ◽  
Frame Difference ◽  
Light And Shadow

in order to solve the adverse effects of strong light and shadow on the test results, a fusion frame difference and background subtraction method in the HSV space is used in this paper. By using frame difference method to solve the effect of strong light, but frame difference method can not detect object when the object do not move, the method of background subtraction can detect it, building Gaussian background model in the HSV space can eliminate shadows. Empirical results show that the method of fusion frame difference and background subtraction in the HSV space can get overcome the effect of strong light and shadows. Fusion background subtraction and frame difference method based on establishing a Gaussian mixture model in HSV space can overcome the disadvantages of the frame difference method, at the same time it can also solve the false detection of object which result from the background subtraction method.

Object Tracking Algorithm Based on Camshift Combining Background Subtraction with Three Frame Difference

2013 ◽  
Vol 373-375 ◽  
pp. 1116-1119 ◽  
Author(s):  
Quan Tang ◽  
Shu Guang Dai ◽  
Jie Yang
Keyword(s):  
Probability Distribution ◽  
Object Tracking ◽  
Difference Method ◽  
Background Subtraction ◽  
Tracking Algorithm ◽  
Target Area ◽  
Characteristic Parameters ◽  
Subtraction Method ◽  
Frame Difference ◽  
Camshift Algorithm

Camshift tracking algorithm is based on probability distribution of color , it is susceptible to be interfered by the same color in the background, which will lead to the failure of the target tracking. To overcome this problem it presented an improved Camshift tracking algorithm. It combined background subtraction method with three frame difference method to detect target, got rectangular characteristic parameters of the motion target area as the Camshift initialization parameters, replaced the general Camshift algorithm which is based on color feature. Experimental results show that Camshift algorithm combining the background subtraction method with three frame difference method can meet the requirements of the real-time and stability to a certain extent.

Improved Moving Target Detection Technology

2014 ◽  
Vol 971-973 ◽  
pp. 1628-1632 ◽  
Author(s):  
Xiao Hui Jin ◽  
Wei Yang ◽  
Qian Jin Liu ◽  
Di Zhao ◽  
Sheng Xu
Keyword(s):  
Difference Method ◽  
Background Subtraction ◽  
Detection System ◽  
Ccd Camera ◽  
Target Image ◽  
Target Region ◽  
Difference Image ◽  
Frame Difference ◽  
Detection Technology ◽  
The Difference

In order to detect target clearly, a detection system based on DM642 was designed. The system used improved frame-difference method combined with the background subtraction to detect target. First, the CCD camera scanned the surroundings step by step, then the background model was built, and improved three-frame-difference method was used to get the three-frame-difference image. The target image was the difference of target region extracted by three-frame-difference method and the target region extracted by background subtraction method. Experiments showed that the target image had less interference and a clear profile.

A Motion Image Detection Method Based on the Inter-Frame Difference Method

2014 ◽  
Vol 490-491 ◽  
pp. 1283-1286 ◽  
Author(s):  
Yuan Hang Cheng ◽  
Jing Wang
Keyword(s):  
Target Detection ◽  
Difference Method ◽  
Background Subtraction ◽  
Vision System ◽  
Robot Vision ◽  
Main Idea ◽  
Image Method ◽  
Detection Model ◽  
Difference Image ◽  
Frame Difference

Mobile robot vision system based on image information on environment, to make it automatic separation from obstacles and achieve precise mathematical description of obstacles, we construct detection model which combined by the frame difference method and background subtraction for target detection, comprehensive utilization of the main idea of three frame difference image method, the background subtraction and frame difference method combined to complement each other, thereby overcoming each other's weaknesses and improving the effect of target detection, experiment results show that this method can effectively improve the efficiency of target detection.

scholarly journals Research on intelligent substation monitoring by image recognition method

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Weijie Tang ◽  
Honggang Chen
Keyword(s):  
Image Recognition ◽  
Difference Method ◽  
Gaussian Mixture ◽  
Moving Target ◽  
Recognition Method ◽  
Active Target ◽  
Frame Difference ◽  
Improved Algorithm

AbstractThis study mainly analyzed the improved three-frame difference algorithm for the identification of active targets in the intelligent substation. The improved three-frame difference algorithm introduced the Gaussian mixture background algorithm on the basis of the traditional three-frame difference method. The Gaussian mixture background algorithm, traditional three-frame difference method, and improved three-frame difference method were tested in the actual substation. The results showed that the improved difference method eliminated the non-target background more thoroughly when recognizing the moving target in the image; in the tested video, the improved algorithm had the highest precision and recall ratios for the active target in the video. To sum up, the improved three-frame difference method can more accurately and effectively identify the active targets in the monitoring video, so as to provide an effective support for the unmanned monitoring of intelligent substation.

scholarly journals Application of Image Processing and Three-Dimensional Data Reconstruction Algorithm Based on Traffic Video in Vehicle Component Detection

2017 ◽  
Vol 2017 ◽  
pp. 1-16
Author(s):  
Gang Li ◽  
Huansheng Song ◽  
Shuyu Wang ◽  
Jinliang Kong
Keyword(s):  
Background Subtraction ◽  
Three Dimensional ◽  
Vehicle Detection ◽  
Reconstruction Algorithm ◽  
Gaussian Mixture ◽  
Detection Accuracy ◽  
License Plate ◽  
Surveillance Systems ◽  
Subtraction Method ◽  
2D Images

Vehicle detection is one of the important technologies in intelligent video surveillance systems. Owing to the perspective projection imaging principle of cameras, traditional two-dimensional (2D) images usually distort the size and shape of vehicles. In order to solve these problems, the traffic scene calibration and inverse projection construction methods are used to project the three-dimensional (3D) information onto the 2D images. In addition, a vehicle target can be characterized by several components, and thus vehicle detection can be fulfilled based on the combination of these components. The key characteristics of vehicle targets are distinct during a single day; for example, the headlight brightness is more significant at night, while the vehicle taillight and license plate color are much more prominent in the daytime. In this paper, by using the background subtraction method and Gaussian mixture model, we can realize the accurate detection of target lights at night. In the daytime, however, the detection of the license plate and taillight of a vehicle can be fulfilled by exploiting the background subtraction method and the Markov random field, based on the spatial geometry relation between the corresponding components. Further, by utilizing Kalman filters to follow the vehicle tracks, detection accuracy can be further improved. Finally, experiment results demonstrate the effectiveness of the proposed methods.

Multiple vehicles detection and tracking for intelligent transport systems using machine learning approaches

2019 ◽  
Vol 70 (3) ◽  
pp. 214-224
Author(s):  
Bui Ngoc Dung ◽  
Manh Dzung Lai ◽  
Tran Vu Hieu ◽  
Nguyen Binh T. H.
Keyword(s):  
Machine Learning ◽  
Gaussian Mixture ◽  
Research Field ◽  
Transport Systems ◽  
Learning Approaches ◽  
Subtraction Method ◽  
Intelligent Transport Systems ◽  
Intelligent Transport ◽  
Detection And Tracking ◽  
Multiple Vehicles

Video surveillance is emerging research field of intelligent transport systems. This paper presents some techniques which use machine learning and computer vision in vehicles detection and tracking. Firstly the machine learning approaches using Haar-like features and Ada-Boost algorithm for vehicle detection are presented. Secondly approaches to detect vehicles using the background subtraction method based on Gaussian Mixture Model and to track vehicles using optical flow and multiple Kalman filters were given. The method takes advantages of distinguish and tracking multiple vehicles individually. The experimental results demonstrate high accurately of the method.

Sign in / Sign up

Export Citation Format

Share Document