Weapons Detection in Visual Data

Automatic detection of weapons is significant for improving security and well being of individuals, nonetheless, it is a difficult task due to large variety of size, shape and appearance of weapons. Viewpoint variations and occlusion also are reasons which makes this task more difficult. Further, the current object detection algorithms process rectangular areas, however a slender and long rifle may really cover just a little portion of area and the rest may contain unessential details. To overcome these problems, we propose Orientation Aware Weapons Detection algorithm which provides oriented bounding box and improved detection performance of weapons. The proposed model provides orientation not only using angle as classification problem by dividing angle into eight classes but also angle as regression problem. For training our model of weapon detection, a dataset comprising of more than six thousand weapons images is gathered from the web and then manually annotated with position oriented bounding boxes. The proposed model is evaluated on this dataset, and the comparative analysis with off-the shelf object detectors yields superior performance of the proposed model. The dataset and the implementation is publicly available at at this github link


Methodology

Model Architecture


People

Faculty

  • Dr Muhammad Moazam Fraz
  • Dr Muhammad Shahzad

Students

  • Nazeef ul Haq
  • Taufial Sajjad Shah

Publications

Under Review


You may also like...