Moving Object Detection using OpenCV
Moving Object Detection
Platform : Python
Delivery Duration : 3-4 working Days
100 in stock
In this project proposed two novel shape features i.e., Hausdorff Dimension and contour signature is implemented for classifying a lymphocytic cell nucleus. NN Classifier is employed for classification.
The project presents moving object detection based on background subtraction under Daubechies wavelet transform domain for video surveillance system. The object detection in frequency domain will be approached to segment objects from foreground with absence of background noise. Initially it starts with background initialization by choosing start frame or taking initial few frames with approximate median method. Then, Daubechies wavelet transform is applied to both current and initialized background frame generates sub bands of low and high frequencies. Frame differencing will be done in this sub bands followed by edge map creation and image reconstruction. In order to remove some unwanted pixels, morphological erosion and dilation operation is performed for object edge smoothness. The proposed approach has some advantages of background noise insensitiveness and invariant to varying illumination or lighting conditions. It also involves background updating model based on current frame and previous background frame pixels comparisons. After the object detection, performance of method will be measured (between frame ground truth and obtained result) through metrics such as sensitivity, accuracy, correlation and peak signal to noise ratio. This object detection also helps to track detected object using connected component analysis. The simulated result shows that used methodologies for effective object detection has better accuracy and with less processing time consumption rather than existing methods.
- Threshold based segmentation
- Gaussian mixture model
- Color histogram and gradient based segmentation
- It is sensitive illumination changes leads to more background noises
- It is time consuming process
- It is not provides better results due to varying light conditions, shadows and other occlusions
Background subtraction based Effective moving object detection using, Daubechies wavelet transform, frame differencing and approximate median based background update
- Daubechies wavelet transform
- Frame Differencing
- Morphological filtering
- Updating Background
- Performance measures (Sensitivity/Accuracy/PSNR/Correlation)
- Better accuracy in segmentation under various illuminations
- Less time consuming process
- Flexibility in background updating model
- It is less sensitive to background noise
- Video surveillance
- Machine Vision systems
- Object Recognition
By this proposed system, the object can be identified in the video surveillance so that the accuracy of the object identification is high.
 W. Hu, T. Tan, “A Survey on Visual Surveillance of Object Motion and Behaviors”, IEEE Trans. Systems, Man, and Cybernetics, Vol. 34, No. 3, pp. 334-352, 2006
 S.C. Cheung and C. Kamath, “Robust techniques for background subtraction in urban traffic video,” Video Communications and Image Processing, SPIE Electronic Imaging,
UCRL Conf. San Jose, vol.200706, Jan 2004.
 N. McFarlane, C. Schofield, “Segmentation and tracking of piglets in images”, Machine Vision Application, Vol. 8, No. 3, pp. 187-193, 1995
 C. Stauffer , W.E.L. Grimson, “Adaptive background mixture models for real-time tracking,” In Proc. Computer Vision and Pattern Recognition conference ,pp. 246-252, 1999.
Z. Zivkovic and F. van der Heijden,” Efficient adaptive density estimation per image pixel for the task of background subtraction”, Pattern Recognition Letters, Vol. 27 No.7, pp. 773–780, 2006.
 F-H. Cheng, Y-L. Chen, “Real time multiple objects tracking and identification based on discrete wavelet transform”, Elsevier journal of Pattern Recognition, Vol. 39, No. 6, pp. 1126–1139, 2006.
A. Khare, U. S. Tiwary, W. Pedrycz, M. Jeon, “Multilevel adaptive thresholding and shrinkage technique for denoising using Daubechies complex wavelet transform”, The Imaging Science Journal, Vol. 58, No. 6, Dec. 2010, pp. 340-358.