Classification and tracking of traffic scene objects with hybrid camera systems

@article{BarisSchlicht2017ClassificationAT,
  title={Classification and tracking of traffic scene objects with hybrid camera systems},
  author={I. Baris Schlicht and Yalin Bastanlar},
  journal={2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)},
  year={2017},
  pages={1-6}
}
  • I. Baris Schlicht, Y. Bastanlar
  • Published 1 October 2017
  • Computer Science
  • 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
In a hybrid camera system combining an omnidirectional and a Pan-Tilt-Zoom (PTZ) camera, the omnidirectional camera provides 360 degree horizontal field-of-view, whereas the PTZ camera provides high resolution at a certain direction. This results in a wide field-of-view and high resolution camera system. In this paper, we exploit this hybrid system for real-time object classification and tracking for traffic scenes. The omnidirectional camera detects the moving objects and performs an initial… 
View on IEEE
gcris.iyte.edu.tr
6 Citations
Background Citations
1
Methods Citations
2

6 Citations

Citation Type

Citation Type

Automatic Rectification of the Hybrid Stereo Vision System
TLDR
A perspective projection model is proposed to reduce the computation complexity of the hybrid stereoscopic 3D reconstruction and the accuracy and effectiveness of the proposed method for rectifying the dynamic hybrid stereo vision system automatically.
The OmniScape Dataset
TLDR
The proposed framework for generating omnidirectional images using images that are acquired from a virtual environment is presented and the generated OmniScape dataset is explained, which includes stereo fisheye and catadioptric images acquired from the two front sides of a motorcycle.
YOLO based Detection and Classification of Objects in video records
  • Arka Prava Jana, Abhiraj Biswas, Mohana
  • Computer Science
    2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT)
  • 2018
TLDR
The YOLO based detection and classification (YOLOv2) use of GPU (Graphics Processing Unit) to increase the computation speed and processes at 40 frames per second and generates an annotation describing the particular class of object.
A Convolutional Feature Map based Deep Network targeted towards Traffic Detection and Classification
Génération d'images omnidirectionnelles à partir d'un environnement virtuel
Dans cet article, nous decrivons une methode pour generer des images omnidirectionnelles en utilisant des images cubemap et les cartes de profondeur correspondantes, a partir d'un environnement…
Detection and localization of motorway overhead directional signs by convolutional neural networks trained with synthetic images

References

SHOWING 1-10 OF 27 REFERENCES
A real time dual-camera surveillance system based on tracking-learning-detection algorithm
TLDR
By comparing two algorithms of codebook and Tracking-Learning-Detection, it is found that TLD is more robust to illumination variation and the scene of multi motion objects.
Cooperative tracking of moving objects and face detection with a dual camera sensor
TLDR
A sensor for autonomous surveillance capable of continuously monitoring the environment, while acquiring detailed images of specific areas, is described by exploiting an omnidirectional camera and a PTZ camera, assembled together on a single mount.
A Catadioptric and Pan-Tilt-Zoom Camera Pair Object Tracking System for UAVs
TLDR
An innovative sensory system is proposed, that has an omnidirectional imaging device and a pan tilt zoom (PTZ) camera that can track any moving object within its 360° field of view and provide detailed images of it.
Multi-camera Based Traffic Flow Characterization & Classification
We describe a system that employs the use of an omnidirectional camera in tandem with a pan-tilt-zoom (PTZ) camera in order to characterize traffic flows, analyze vehicles, and detect and capture…
Framework for real-time behavior interpretation from traffic video
TLDR
A rule-based framework for behavior and activity detection in traffic videos obtained from stationary video cameras is presented and successful behavior recognition results for pedestrian-vehicle interaction and vehicle-checkpost interactions are demonstrated.
A direct approach for object detection with catadioptric omnidirectional cameras
TLDR
This paper adopts the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features, and describes how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras.
Multi-view structure-from-motion for hybrid camera scenarios
Combining Shape-Based and Gradient-Based Classifiers for Vehicle Classification
TLDR
This paper investigates whether the combined use of shape-based and gradient-based classifiers outperforms the individual classifiers or not, and shows that the combined classifier is superior to theindividual classifiers.
Detection and classification of vehicles from omnidirectional videos using multiple silhouettes
TLDR
The results indicate that using multiple silhouettes increases the classification performance and eliminates most of the wrong decisions which are caused by a poorly extracted silhouette from a single video frame.
Robust classification and tracking of vehicles in traffic video streams
  • B. Morris, M. Trivedi
  • Computer Science
    2006 IEEE Intelligent Transportation Systems Conference
  • 2006
TLDR
A tracking system with the ability to classify vehicles into three classes {sedan, semi, truck+SUV+van} is presented, developed after comparing classification schemes using both vehicle images and measurements.
...
1
2
3
...