3D OBJECT DETECTION USING VISUAL SALIENCY FROM IMAGES
ARNAB PODDER ANKIT PANDEY HRITIKA RAO AINDRILA DAS
What is 3D Object detection?
3D object recognition involves recognizing and determining 3D information, such as the pose, volume, or shape, of user-chosen 3D objects in a photograph or range scan. Typically, an example of the object to be recognized is presented to a vision system in a controlled environment, and then for an arbitrary input such as a video stream, the system locates the previously presented object.
Visual saliency -
Visual salience (or visual saliency) is the distinct subjective perceptual quality which makes some items in the world stand out from their neighbors and immediately grab our attention.
In computer vision, 3D object recognition involves recognizing and determining 3D information, such as the pose, volume, or shape, of user-chosen 3D objects in a photograph or range scan.
In recent years, 3D technologies became popular in the folk gradually with the application in film and television industry. People can see the 3D models almost everywhere, so it’s natural and reasonable to explore the more efficient methods to learn the representation of 3D models. Besides, with the development of computer vision and 3D reconstruction technology, 3D model recognition has become a fundamental task in shape analysis which is the most crucial technology for processing and analyzing 3D data.
This is a 3d object detection system. This is meant to be used to detect 3d object around us, like it can be a chair, shoe, table etc. Here the System take input from the user and make a 3d bounded box of the object as an output.
Image Processing: For image processing we use some packages of Python like OpenCV, Mediapipe. Which helps to detect the 3d object.
Frontend UI Framework: We will be using streamlit