ACADSTAFF UGM
| Title | : | Body Part Boosting Model for Carried Baggage Detection and Classification |
| Author | : |
Wahyono, Ph.D. (1) Joko Hariyono (2) Prof. Kanghyun Jo (3) |
| Date | : | 0 2016 |
| Keyword | : | Carried Baggage Detection Carried Baggage Detection |
| Abstract | : | In the automatic video surveillance system, detecting human carrying baggage is a potentially important objective for security and monitoring purposes in the public spaces. This paper introduces a new approach for detecting and classifying baggage carried by human on the images. It utilizes the spatial information of baggage in relevance to the human body carrying them. A human-baggage detector is modeled by the body parts of human, such as head, torso, leg and baggage parts. The feature descriptors are extracted for each part based on its characteristics and these features are further trained using a support vector machine (SVM) classifier. Especially for a baggage part, a mixture model is built for overcoming a strong variation in shape, size, color, and texture. The boosting strategy constructs a strong classifier by combining a set of weak classifiers which are obtained by training the body part. The proposed method has been extensively evaluated using the public dataset. The experimental results suggested that the proposed method can be one of the alternative approaches for the state-of-the-art in the carried baggage detection and classification system. |
| Group of Knowledge | : | Ilmu Komputer |
| Original Language | : | English |
| Level | : | Internasional |
| Status | : |
Published
|
| No | Title | Action |
|---|