For many smart road applications, objects detection and recognition are one of the most important components. Indeed, precise detection of road objects is a critical task for autonomous urban driving and robotics technologies.
Actually, we are working on the conception of a smart system that consists in detecting and blurring undesirable road objects to anonymize and secure road users.
In this context, we want to know what are the up-to-date methods (Neural approaches, etc.) used for the detection and recognition of road objects (humans, vehicles, license plates, etc.) ? Any ideas ?
Greatly appreciate your review
I think the question needs more details like what are the problems you are facing with existing studies, precise detection is too general. As of current, YOLOv4, YOLOR, and G-RCNN are state-of-the-art in the field of object detection and you can customize them as per your need. The former two are one stage detectors while the latter one is two-stage detector. You can also use DeepSort as well. It depends on your desired task which one you should opt for. Now specific problems can range from stereo disparity, 3-D center point, one or few-shot detection, image modalities like monocular images. I read some paper recently in CVPR and ICCV, I think you should give them a read.
-Center-based 3D Object Detection and Tracking, CVPR 2021
-Few-Shot Batch Incremental Road Object Detection via Detector Fusion, ICCV 2021
-Disentangling Monocular 3D Object Detection: From Single to Multi-Class Recognition, TPAMI 2020.
-
Hi Wissam Kaddah,
Please find some of the benchmarks for related tasks (segmentation, recognition, detection):
Considering the real-time aspects you may also want to checkout:
Dear Prof. Wissam Kaddah,
I have the following research in this area:
Article RT-VC: AN EFFICIENT REAL-TIME VEHICLE COUNTING APPROACH
- Badges
- Science topic
- Similar topics
- Physical Sciences
- Materials Science
- Materials
- Inorganic Materials
- Ceramics
- Glass