Algorithm Optimization of Motion Tracking Based on Optical Flow

2014 ◽  
Vol 926-930 ◽  
pp. 2938-2941
Author(s):  
Dong Ming Liu ◽  
Chao Liu ◽  
Hai Wei Mu
Keyword(s):  
Optical Flow ◽  
Motion Tracking ◽  
Differential Method ◽  
Video Image ◽  
Time Axis ◽  
Algorithm Optimization ◽  
Image Preprocessing ◽  
Smoothing Filter ◽  
Matching Filter ◽  
Non Gaussian

Optical flow is an important kind of video motion tracking algorithm, and Lucas-Kanade (LK) algorithm is an effective differential method in terms of calculating optical flow. The 3D Gaussian smoothing filter is properly introduced in the image preprocessing stage of the LK algorithm, which makes it possible to increase the correlation of the adjacent pixels in the time axis, improve the blur effect of the video image and overcome the 2D Gaussian filters disadvantage that is not suitable for the video image processing. More importantly, the optimized 3D non-Gaussian matching filter is chosen during the 3D derivative calculating, and it is capable of reducing the error rate of the velocity vector calculation and enhancing the calculation accuracy of the optical flow.

scholarly journals A Novel Change Detection Method for Natural Disaster Detection and Segmentation from Video Sequence

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5076
Author(s):  
Huijiao Qiao ◽  
Xue Wan ◽  
Youchuan Wan ◽  
Shengyang Li ◽  
Wanfeng Zhang
Keyword(s):  
Change Detection ◽  
Optical Flow ◽  
Natural Disaster ◽  
Motion Tracking ◽  
Video Sequence ◽  
Monitoring And Evaluation ◽  
Threshold Selection ◽  
Geometric Information ◽  
Flow Estimation ◽  
Key Steps

Change detection (CD) is critical for natural disaster detection, monitoring and evaluation. Video satellites, new types of satellites being launched recently, are able to record the motion change during natural disasters. This raises a new problem for traditional CD methods, as they can only detect areas with highly changed radiometric and geometric information. Optical flow-based methods are able to detect the pixel-based motion tracking at fast speed; however, they are difficult to determine an optimal threshold for separating the changed from the unchanged part for CD problems. To overcome the above problems, this paper proposed a novel automatic change detection framework: OFATS (optical flow-based adaptive thresholding segmentation). Combining the characteristics of optical flow data, a new objective function based on the ratio of maximum between-class variance and minimum within-class variance has been constructed and two key steps are motion detection based on optical flow estimation using deep learning (DL) method and changed area segmentation based on an adaptive threshold selection. Experiments are carried out using two groups of video sequences, which demonstrated that the proposed method is able to achieve high accuracy with F1 value of 0.98 and 0.94, respectively.

scholarly journals Recognition and Analysis of Behavior Features of School-Age Children Based on Video Image Processing

2020 ◽  
Vol 37 (4) ◽  
pp. 603-610
Author(s):  
Zhen Wang
Keyword(s):  
Image Processing ◽  
Optical Flow ◽  
Network Flow ◽  
Video Image ◽  
School Age Children ◽  
School Age ◽  
Surveillance Video ◽  
Flow Network ◽  
Time Flow ◽  
Video Image Processing

School-age children have vastly different behavior features from adults. Most of the relevant studies are theoretical summaries of behavior features of these children, failing to detect the behaviors or recognize the behavior features in an accurate manner. To solve the problem, this paper puts forward a novel method to recognize the behavior features of school-age children through video image processing. Firstly, the authors designed a method to extract static behavior features of school-age children from surveillance video images. Next, the behavior features of school-age children were extracted by optical flow method. On this basis, a dual-network flow neural network (DNFNN) was designed, in which the time flow network processes the dense optical flow of multiple continuous frames of the surveillance video, while the spatial flow network treats the region of interest (ROI) in the static frame from the video. After that, the workflow of the DNFNN was introduced in details. Experimental results fully demonstrate the effectiveness of the proposed network. The research findings provide a reference for the application of video image processing to behavior recognition in other fields.

scholarly journals Digital Video Image Preprocessing Algorithm Based on Embedded System

2021 ◽  
Vol 2074 (1) ◽  
pp. 012004
Author(s):  
Ling Cheng
Keyword(s):  
Embedded System ◽  
Digital Video ◽  
Video Image ◽  
Network Interface ◽  
Median Filtering ◽  
Image Preprocessing ◽  
Filtering Algorithm ◽  
Video Images ◽  
Low Illumination ◽  
Wavelet Image

Abstract To solve the massive noise contained in the images acquired under low illumination, we designed a digital video image Preprocessing device with the denoising function. Based on the embedded CPU and operating system, video images are acquired by the camera. The noise contained in the video images is filtered by the improved median filtering algorithm and wavelet image denoising. Subsequently, the images are transmitted through USB and network interface, and the storage function of image files is implemented. The device can remove the noise contained in videos effectively, which is conducive to performing more advanced processing on the images.

scholarly journals Feature Point Extraction and Motion Tracking of Cardiac Color Ultrasound under Improved Lucas–Kanade Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xiaoli Zhang ◽  
Punan Li ◽  
Yibing Li
Keyword(s):  
Optical Flow ◽  
Speckle Tracking ◽  
Motion Tracking ◽  
Color Doppler ◽  
Color Doppler Ultrasound ◽  
Feature Points ◽  
Sift Algorithm ◽  
Calculation Time ◽  
Tracking Method ◽  
Optical Flow Method

The purpose of this research is to study the application effect of Lucas–Kanade algorithm in right ventricular color Doppler ultrasound feature point extraction and motion tracking under the condition of scale invariant feature transform (SIFT). This study took the right ventricle as an example to analyze the extraction effect and calculation rate of SIFT algorithm and improved Lucas–Kanade algorithm. It was found that the calculation time before and after noise removal by the SIFT algorithm was 0.49 s and 0.46 s, respectively, and the number of extracted feature points was 703 and 698, respectively. The number of feature points extracted by the SIFT algorithm and the calculation time were significantly better than those of other algorithms ( P < 0.01 ). The mean logarithm of the matching points of the SIFT algorithm for order matching and reverse order matching was 20.54 and 20.46, respectively. The calculation time and the number of feature points for the SIFT speckle tracking method were 1198.85 s and 81, respectively, and those of the optical flow method were 3274.19 s and 80, respectively. The calculation time of the SIFT speckle tracking method was significantly lower than that of the optical flow method ( P < 0.05 ), and there was no statistical difference in the number of feature points between the SIFT speckle tracking method and the optical flow method ( P > 0.05 ). In conclusion, the improved Lucas–Kanade algorithm based on SIFT significantly improves the accuracy of feature extraction and motion tracking of color Doppler ultrasound, which shows the value of the algorithm in the clinical application of color Doppler ultrasound.

Sign in / Sign up

Export Citation Format

Share Document