Performance of optical flow techniques
International Journal of Computer Vision
Independent Motion Detection in 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Adaptive Tracking to Classify and Monitor Activities in a Site
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Background Subtraction Using Markov Thresholds
WACV-MOTION '05 Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05) - Volume 2 - Volume 02
Motion Detection Based on Temporal Difference Method and Optical Flow field
ISECS '09 Proceedings of the 2009 Second International Symposium on Electronic Commerce and Security - Volume 02
Hi-index | 0.00 |
A camera mounted on a MICro Aerial Vehicle (MICAV) provides an excellent means to monitor large areas of a scene. In this paper, we present a novel approach for detecting motion regions in video sequence observed by a moving MICAV. Foreground object segmentation is done in four levels. In the first level, we use Pearson correlation coefficient (rab) to segment foreground from background. In the second level, we apply, self shadow removal algorithm based on Difference in Mean (Z) method. And in third and fourth stage, any remaining background spurious noise is removed concurrently, first calculating global histogram and then using local histogram based methods using HSI color space. The experiment is conducted on MICAV video and result shows the effectiveness of the proposed technique.