Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟬𝟳 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 Researcher of Polytechnique Montréal published 𝗣𝗼𝗹𝘆𝗧𝗿𝗮𝗰𝗸 for fast multi-object tracking and segmentation Follow me for a similar post: 🇮🇳 Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published NeurIPS2021. 🔸 Multi-object tracking and segmentation (MOTS) is a fairly novel task that combines instance segmentation and multi-object tracking. It consists of associating and segmenting instances of objects corresponding to predetermined classes across multiple consecutive frames. This problem is important for many applications, in particular for intelligent transportation systems (ITS) and driver assistance and automation technologies. 🔸PolyTrack, which is based on polygonal masks. Polytrack can be thought of as an improved traditional multi-object tracker providing something better than bounding boxes, that is bounding polygons, at almost no additional cost. I ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸In this paper, we present a novel method called Polytrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps of their centre keypoint.  🔸For each of them, a rough segmentation is done by computing a bounding polygon over each instance instead of the traditional bounding box. Tracking is done by taking two consecutive frames as input and computing a centre offset for each object detected in the first frame to predict its location in the second frame.  🔸 A Kalman filter is also applied to reduce the number of ID switches. Since our target application is automated driving systems, we apply our method to urban environment videos. We trained and evaluated Polytrack on the MOTS and KITTIMOTS datasets. Results show that tracking polygons can be a good alternative to bounding box and mask tracking.  ------------------------------------------------------------------- #computervision #artificialintelligence #innovation -------------------------------------------------------------------