Motion detection using Lucas Kanade algorithm and application enhancement

Siong, Lee Yee; Mokri, Siti Salasiah; Hussain, Aini; Ibrahim, Norazlin; Mustafa, Mohd. Marzuki

doi:10.1109/iceei.2009.5254757

Cited by 17 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case, f x and f y are both directional derivatives with θ = 0 and θ = 90 • We use the Lucas and Kanades methods [27][28] using small windows (in our case, we used a 3 by 3 window in the region ρ), and the least squares method.…”

Section: B Temporal Modeling Using the Optical Flow Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Human activity recognition based on mid-level representations in video surveillance applications

Abdelhedi¹,

Wali²,

Alimi³

2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Human Action Recognition methods have prospered during the last decade. They seek to automatically analyze ongoing activities in different camera views by using machinelearning algorithms in video sequences. Various human action recognition methods match local features and global features using action class labels in which abundant visual spatio-temporal information can hardly be generalized. To overcome this problem, we propose a novel notion of mid-level representations to construct a discriminative and informative semantic concept for human action recognition. This work introduces a mid-level representation based on the Optical Flow (OF) method, Hu and Zernike moment together. First we extract from each video, U h and Uv motion vectors by forming motions curvatures. Second, we determine the Hu moment and Zernike that serve as the feature vector of an action. Our method was tested and evaluated through a classification of the KTH and Weizmann datasets, with an Artificial Neural Network classifier (ANN). The results prove the accuracy of the suggested approach.

show abstract

Section: B Temporal Modeling Using the Optical Flow Methodsmentioning

confidence: 99%

“…In this context, we use the Lucas-Kanade algorithm[27][28] derivatives.For each frame, f (x; y; t) denotes the pixel value at (x; y) position at time t. The new position of this pixel moves to f (x + δx; y + δy; t + δt) in time δt.…”

mentioning

confidence: 99%

Human activity recognition based on mid-level representations in video surveillance applications

Abdelhedi¹,

Wali²,

Alimi³

2016

2016 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…The LK-OFE algorithm finds the flow vector of features by minimizing the sum of squared error between two images. It exhibits excellent performance and has been used in many applications [13][14][15][16][17][18]. However, there is a tradeoff between local accuracy and robustness when choosing the window size.…”

Section: Introductionmentioning

confidence: 99%

Area-Efficient Vision-Based Feature Tracker for Autonomous Hovering of Unmanned Aerial Vehicle

et al. 2020

View full text Add to dashboard Cite

In this paper, we propose a vision-based feature tracker for the autonomous hovering of an unmanned aerial vehicle (UAV) and present an area-efficient hardware architecture for its integration into a flight control system-on-chip, which is essential for small UAVs. The proposed feature tracker is based on the Shi–Tomasi algorithm for feature detection and the pyramidal Lucas–Kanade (PLK) algorithm for feature tracking. By applying an efficient hardware structure that leverages the common computations between the Shi–Tomasi and PLK algorithms, the proposed feature tracker offers good tracking performance with fewer hardware resources than existing feature tracker implementations. To evaluate the tracking performance of the proposed feature tracker, we compared it with the GPS-based trajectories of a drone in various flight environments, such as lawn, asphalt, and sidewalk blocks. The proposed tracker exhibited an average accuracy of 0.039 in terms of normalized root-mean-square error (NRMSE). The proposed feature tracker was designed using the Verilog hardware description language and implemented on a field-programmable gate array (FPGA). The proposed feature tracker has 2744 slices, 25 DSPs, and 93 Kbit memory and can support the real-time processing at 417 FPS and an operating frequency of 130 MHz for 640 × 480 VGA images.

show abstract