Vehicle Re-Identification for traffic surveillance
In an Intelligent traffic monitoring system vehicle re-id plays an import role as vehicle re-id is a process in which we are going to detect a vehicle and then re-identify the vehicle from our database of vehicles. This can play an important role in the field of live monitoring or tracking the vehicles or doing forensic analysis like finding patterns of different vehicles etc. This requires intelligent and efficient algorithms and to solve this problem, we will be using the deep learning which is state of the art for many problems these days. Vehicle re-identification helps to determine whether a given vehicle has appeared in another camera. The technology is useful to automatically locate a certain vehicle in a network of cameras, mainly for surveillance applications. In practice, issues like variations in illumination changes, camera view angles, vehicle positions, etc. are the typical challenges that need to be solved by the vehicle re-identification technology.
In real-world practice, humans can treat this task in a progressive manner. For instance, if the security ofﬁcer needs to ﬁnd a suspect car in a city with large-scale video surveillance networks, appearance attributes such as models,types, and colors can be initially used to ﬁnd similar vehicles and reduce the search ﬁeld. Then, they can identify the targets precisely from the ﬁltered vehicles by matching the license plates, which can reduce the enormous workload. Meanwhile,they will search videos recorded by cameras from near to far positions and from close to distant time range. Therefore,the contextual information such as spatio temporal cues thus can decidedly assist in the search process.
Generic Vehicle re-Identification pipeline: (a) depicts the result of vehicle detection in natural scenes in the input images/videos feed from non-overlapping camera views; (b) illustrates the concept of vehicle re-identification where the vehicle in the gallery images are represented using discriminative features which are then matched with the probe images using similarity/feature learning procedure, i.e., given the probe/query images we perform vehicle matching using similarity/dissimilarity learning to determine the set of same/similar vehicles in the gallery containing multiple images of individual vehicles captured from different multi-view cameras with varying illuminations.
- R M S Bashir, M Shahzad, M M Fraz , “VR-PROUD: Vehicle Re-identification using PROgressive Unsupervised Deep architecture”, Pattern Recognition, Vol. 90 , No. 1, PP. 52-65, Jan, 2019. IF: 5.898
- R M S Bashir, M Shahzad, M M Fraz , , “DUPL-VR: Deep Unsupervised Progressive Learning for Vehicle Re-Identification”, Proceedings of the 13th International Symposium on Visual Computing, Nov, 2018, Las Vegas , United States.