IdentCAR is an intelligent monitoring system dedicated to vehicle identification based on recognition of cars’ manufacturers and brands, as well as on their registration numbers. Additionally IdentCAR allows for detection of car transit routes on the basis of indications from cameras with the implemented functionalities of the system.
IdentCAR system was developed in the scope of a research project INSIGMA – “Intelligent Information System for detection and recognition”, realized in cooperation with University of Computer Engineering and Telecommunications (WSTKT) in Kielce. One of the key objectives of the research was development of tools which could support Police Services in preventing measures and in the prosecution of perpetrators of road traffic offences and crimes. IdenCAR is an answer to requirements from Police Services. It allows for searching through a monitoring content either off-line or on-line (based on real time video from camera) for vehicles which were involved in a specific traffic offence or crime. Testimonies of witnesses can be a supportive information for effective search – besides an estimated time of such event, witnesses can also suggest brand or car model, whole or part of car number plate. On the basis of these, even incomplete testimonies, IdentCAR may be helpful for indicating potential offenders.
The main component of IdentCAR system is a Smart Camera system, known as the iCamera system, designed for the Surveillance of Vehicles in Intelligent Transportation Systems.
The iCamera’s system backbone (the Camera Core), receives the video stream from the Camera IP, and decodes and passes it on to subsequent modules. The decoded video frames are initially passed on to the Global Detection and Extraction (GDE) module. The task of this module is to detect (on a video frame from the camera) and then to extract (by cropping this frame) two Regions of Interest (ROIs). One of them – a sub-image containing the grill part of a car together with its headlights and indicator lights is for the Make & Model Recognition of Cars (MMR) and the Color Recognition (CR) modules. The other – a sub-image limited to the license plate area is for the License Plate Recognition (LPR) module.
Both ROIs are detected using two different Haar-like detectors, which have been trained concurrently according to MMR (CR) and LPR needs. Successful ROI detection (equivalent to car detection in FOV) causes the GDE to activate the MMR, CR and LPR modules.
After activation, the MMR, CR and LPR modules individually process ROIs passed to them from the GDE, and send the results of this processing back to the Camera Core.
Information given later in this page provides some useful information (and test datasets) related to research on Make & Model Recognition of Cars (MMR).
The most common and well known application from the category of traffic management and monitoring is the Automatic Number Plate Recognition (ANPR). However, due to growing demand which meets mayor advance of technical capabilities, also other categories of vehicle classication have recently been added. One of the main and relatively newly added functionality, among such as color and vehicle type distinguishing (between lorries and passenger cars for instance), is make and model recognition (MMR) of cars.
Unlike vehicle type distinguishing, MMR is aimed at correct identification of car make and model within a given type.
Our currently available training (db) & test (query) datasets to be used in analysis of MMR approaches can be downloaded from here:
Please properly cite our works if you find them and the above datasets useful.
This supports our future development works.
- R. Baran, A. Dziech, A. Zeja, “A capable multimedia content discovery platform based on visual content analysis and intelligent data enrichment”, Multimedia Tools and Applications [ISSN: 1380-7501], DOI: 10.1007/s11042-017-5014-1.
- J. Nawała, M. Leszczuk, M. Zajdel, R. Baran, “Software package for measurement of quality indicators working in no-reference model”. Multimedia Tools and Applications [ISSN: 1380-7501], DOI: 10.1007/s11042-016-4195-3.
- R. Baran, T. Ruść, P. Fornalski, “A Smart Camera for the Surveillance of Vehicles in Intelligent Transportation Systems”. Multimedia Tools and Applications [ISSN: 1380-7501], Vol. 75, Issue 17, pp 10471–10493, 2016,
- P. Ślusarczyk, R. Baran, “Piecewise-linear subband coding scheme for fast image decomposition”. Multimedia Tools and Applications [ISSN: 1380-7501], Vol. 75, Issue 17, pp 10649–10666, 2016, DOI: 10.1007/s11042-014-2173-1.
- R. Baran, A. Glowacz, A. Matiolanski, “The efficient real- and non-real-time make and model recognition of cars”, Multimedia Tools and Applications [ISSN: 1380-7501], Vol. 74, Issue 12, pp 4269–4288, 2015, DOI: 10.1007/s11042-013-1545-2.
- L. Janowski, P. Kozłowski, R. Baran, P. Romaniak, A. Głowacz, T. Ruść, “Quality assessment for a visual and automatic license plate recognition”. Multimedia Tools and Applications [ISSN: 1380-7501],, Vol. 68, Issue 1, pp 23-40, 2014,
- R. Baran, P. Partila, R. Wilk, “Automated Text Detection and Character Recognition in Natural Scenes Based on Local Image Features and Contour Processing Techniques”, In: Karwowski W., Ahram T. (eds) Intelligent Human Systems Integration. IHSI 2018. Advances in Intelligent Systems and Computing, Vol. 722, pp 42-48, Springer, Cham [ISBN: 978-3-319-73887-1], 2017,
- R. Baran, A. Dziech, J. Wassermann, “Contour Extraction and Compression Scheme Utilizing Both the Transform and Spatial Image Domains”, In: Dziech A., Czyżewski A. (eds) Multimedia Communications, Services and Security. MCSS 2017. Communications in Computer and Information Science, Vol 785, pp 1-15, Springer, Cham [ISBN: 978-3-319-69910-3], 2017,
- R. Baran, “Efficiency Investigation of BoF SVT and Pyramid Match Algorithms in Practical Recognition Applications”, Proceedings of the 2017 IEEE Int. Conf. on Mathematics and Computers in Sciences and in Industry (MCSI), pp 171-178 [ISBN: 978-1-5386-2820-1], Corfu Island, Greece, 2017,
- R. Baran, F. Rudziński, A. Zeja, “Face Recognition for Movie Character and Actor Discrimination Based on Similarity Scores”, Proceedings of the 2016 IEEE Int. Conf. on Computational Science and Computational Intelligence (CSCI),
pp 1333-1338, [ISBN: 978-1-5090-5510-4], Las Vegas, NV, USA, 2016,
DOI: 10.1109/CSCI.2016.0249, WOS:000405582400241,
- R. Baran, A. Zeja, P. Ślusarczyk, “An Overview of the IMCOP System Architecture with Selected Intelligent Utilities Emphasized”. In: Dziech A., Leszczuk M., Baran R. (eds) Multimedia Communications, Services and Security. MCSS 2015. Communications in Computer and Information Science, Vol 566, pp 3-17, Springer, Cham [ISBN: 978-3-319-26403-5], 2015,
DOI: 10.1007/978-3-319-26404-2_1, WOS: 000369300700001
- R. Baran, A. Zeja, “The IMCOP System for Data Enrichment and Content Discovery and Delivery”. Proceedings of the 2015 Int. Conf. on Computational Science and Computational Intelligence (CSCI 2015), pp 143-146 [Electronic ISBN: 978-1-4673-9795-7], Las Vegas, USA, 2015,
DOI: 10.1109/CSCI.2015.137, WOS:000380405100027
- R. Baran, Ruść T., Rychlik M, “A Smart Camera for Traffic Surveillance”. In: Dziech A., Czyżewski A. (eds) Multimedia Communications, Services and Security. MCSS 2014. Communications in Computer and Information Science,
Vol 429, pp 1-15, Springer, Cham [ISBN: 978-3-319-07568-6], 2014,
DOI: 10.1007/978-3-319-07569-3_1, WOS: 000342898000001
- M. Leszczuk, R. Baran, Ł. Skoczylas, M. Rychlik, P. Ślusarczyk, “Public Transport Vehicle Detection Based on Visual Information”. In: Dziech A., Czyżewski A. (eds) Multimedia Communications, Services and Security. MCSS 2014. Communications in Computer and Information Science, Vol 429, pp 16-28, Springer, Cham [ISBN: 978-3-319-07568-6], 2014,
DOI: 10.1007/978-3-319-07569-3_2, WOS:000342898000002
- R. Baran, A. Kleszcz, “The Efficient Spatial Methods of Contour Approximation”. Proceedings of the 2014 IEEE Int. Conf. on Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA 2014), pp. 116-121 [ISBN: 978-8-3620-6518-9], Poznań, Poland, 2014, WOS: 000393515800022
We do not take any responsibility on damage or other problems caused by using these software or data sets.