Abstract
Today, video is a common medium for sharing information. Navigating the internet to download a certain form of video, it takes a long time, a lot of bandwidth, and a lot of disk space. Since sending video over the internet is too costly, therefore video summarization has become a critical technology. Monitoring vehicles of people from a security and traffic perspective is a major issue. This monitoring depends on the identification of the license plate of vehicles. The proposed system includes training and testing stages. Training stage comprises: video preprocessing, Viola-Jones training, and Support Vector Machine (SVM) optimization. Testing stage contains: test video preprocessing, car plate (detection, cropping, resizing, and grouping detecting test car plate, feature extraction using HOG feature. The total time of local recorded videos is (19.5 minutes), (15.5 minutes) for training, and (4 minutes) for testing. This means, (79.5%) for training and (20.5%) for testing. The proposed video summarization has got maximum accuracy of (86%) by using Viola-Jones and SVM by reducing the number of original video frames from (7077) frames to (1200) frames. The accuracy of the Viola-Jones object detection process for training 700 images is (97%). The accuracy of the SVM classifier is (99.6%).
Highlights
In recent years, sudden technical advancements in video data creation and its storage is improved a lot
While the second is dynamic video summarization called dynamic video skimming, video skim, moving image abstract, or moving storyboard that summarizing the first video to video as short as possible that provides a global picture of the video
The number of cascaded stages (Num Cascade Stage) is an important factor in the proposed model, in the Viola-Jones training table (4.6). In this table the accuracy fluctuates as the value of Num Cascade Stage was increased the accuracy of detection was increased, but the time taken for car plate detection was be increased
Summary
Sudden technical advancements in video data creation and its storage is improved a lot. The video was retrieved based on features such as Graph-Based Visual Saliency This approach used Greedy Search Algorithm can be mainly divided into two parts: First, Perceptual video description where a description in line with human vision properties plays a key role in deciding the frames to be used for the review. This approach fits best for photo images, where the foregrounds in the mainframes are stitched on the backdrop to achieve a single condensed picture.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call