Content-based retrieval of video data has become a challenging and important issue. Video contains several types of audio and visual information which are difficult to extract, combine or trade-off in common video information retrieval. With the development and application of the information technology, the kinds and amount of video reconnaissance equipment on battlefield become more and more. Problem in the battlefield video is comprising of much volume of data and large redundancy. Content based video retrieval provides the good method to decrease the redundancy in the battlefield. Video key frames are pictures that can represent main content of the shot, the key-frame extraction has been the foundation of video analysis and content-based retrieval. Key frame extraction aims at finding a small collection of salient images extracted from a video sequence for visual content summarization.
Target recognition based on the combination of target region and shape features present. When the target is moving, the features of the target are changed. Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications Detection of moving object in video provides the focus of attention for recognition, classification and activity analysis.
1. Redundant frames elimination.
2. Key frames selection.
3. Video shot detection.
4. Moving Target detection
5. Camouflage detection.
1. Battle field video of India Pakistan war action video.
2. Histogram difference: processing of battlefield video requires quick time and real time so, the histogram difference method is adopted. Histogram is described as each color histogram, which is formed by calculating the volume of some special color pixels on a frame image. Histogram method indicates general distribution of the image pixels color in the frame.
3. Key frame extracted: the extraction of key frame is the selection of a frame image in the shot to represent the video content of the shot. The key frames may be one or some frames reflecting the main information in the shot. By the calculation of key frame extraction, the redundancy decreases.
4. Background Subtraction algorithm for detecting moving objects/target and camouflage detection. Background subtraction algorithm must be robust against changes in illumination. It should avoid detecting non-stationary background objects such as moving leaves, rain, snow, and shadows cast by moving objects. Finally, its internal background model should react quickly to changes in background such as starting and stopping of vehicles
Operating System : Windows 95/98/2000/XP
Technology : VC++
Tools : MATLAB
Processor :1.1 GHz
RAM. : 128 MB
Hard Disk :20 GB
CD-ROM Drive : 52x
MONITOR : 800x600 minimum resolution at 256 colors minimum.
INNOVATION / CONTRIBUTION TO THE FIELD :
In the proposed system, the key frames can replace the battlefield video which will help in diminishes the data volume largely and helps in redundancy elimination. Detecting the moving objects in the video helps in tackle the camouflage problem. The system help in detecting accuracy and speed of the moving object in video.