Object detection from images and videos
Deep learning has been widely applied to various computer vision tasks such as image classification, object detection, semantic segmentation, and human pose estimation. When we intend to solve the object detection problem from images, the whole process starts from object classification. Then we perform object localization and finally, we perform the object detection.
Note
This project is highly inspired by the Java Autonomous driving – Car detection article by Klevis Ramo (http://ramok.tech/). Also, some theoretical concepts are used (but significantly extended for this need) with due permission from the author.
Object classification, localization, and detection
In an object classification problem, from a given image (or video clip), we're interested to know if it contains a region of interest (ROI) or object. More formally, "the image contains a car" versus "the image does not contain any car." To solve this problem, over the last few years, ImageNet...