IMAGE-BASED APPROACH FOR VEHICLE MODEL RE-IDENTIFICATION
Annotation
Subject of Research. The paper presents a study of the existing methods for identifying and comparing the features of objects used in the re-identification task of vehicle model by its image. This task is one of the most important tasks facing automated traffic control systems, and it is solved by comparing the features of the vehicle being verified with a certain set of features obtained earlier by the monitoring system. Then decision is made whether the compared samples belong to the same vehicle model or to different ones. A method is proposed for feature vectors extraction and comparison of vehicle model according to its image. The method is based on the use of convolutional neural networks. The proposed approach is compared with existing algorithms for vehicle model re-identification by the accuracy criterion. Method. The paper describes the approach for vehicle image feature vector extraction and its subsequent comparison with the reference vector for similarity examination. The approach is based on the method of feature vector extraction, using classification convolutional neural network, and on comparison criterion for feature vectors applying the estimate of coincidental features. Main Results. The proposed vehicle model verification method demonstrates accuracy comparable to modern analogous in scenarios when the testing data have characteristics that coincide with training ones (similar camera model and camera angles are used; the level of lighting and noise are similar; models of re-identifiable vehicles are contained in the dataset used for the classification network training). In case of data significantly different from the training dataset, the method shows a lower computational complexity and uses smaller size of used feature vector and demonstrates significantly higher relative accuracy of re-identification. Practical Relevance. The proposed approach is practically applicable in vehicle identification task for highly loaded traffic control systems.
Keywords
Постоянный URL
Articles in current issue
- RESEARCHOF MAGNETIC RESONANCE QUALITY FACTOR DEPENDENCE ON CESIUM DISTRIBUTION IN QUANTUM ROTATION SENSOR CELL
- METHODS OF MECHANICAL NOISE IMPACT SUPPRESSION DURING STREAMER TOWING PROCESS USING FIBER BRAGG GRATINGS
- COMPARISON OF PROTEIN SECONDARY STRUCTURE CALCULATION METHODS BASED ON INFRARED SPECTRA DECONVOLUTION
- AUTOMATION OF ATHERMAL CEMENTED DOUBLET SYNTHESIS
- VALIDATION OF SPECTRAL MODEL OF DIGITAL COLOR CAMERA FOR IMAGE PROCESSING IN COLOR-VISION BASED OPTICAL CORRELATION-EXTREME AIRCRAFT NAVIGATION SYSTEM
- IMPACT OF PROXIMITY EFFECT ON RESOLUTION IN IMAGES RECONSTRUCTED BY COMPUTER-GENERATED HOLOGRAMS
- DEVELOPMENT AND RESEARCH OF COMPUTED TOMOGRAPHY METHODS
- LOCALIZATION OF MOBILE ROBOT WITH PARTICLE FILTER AT DETECTION AND SEGMENTATION OF OBJECTS
- SYNTHESIS OF LOW-AGGLOMERATED YAG:Yb NANOPOWDERS FOR TRANSPARENT CERAMICS BY METHOD OF REVERSE CO-PRECIPITATION FROM CHLORIDE SALTS
- ALGEBRAIC BAYESIAN NETWORKS:SEQUESTERED FUSION OF KNOWLEDGE PATTERNS UNDER INFORMATION DEFICIENCY CONDITIONS
- ELECTRONIC FILE FORMATION TECHNIQUE
- DIGITIZATION DEVELOPMENT DIRECTIONS OF NATIONAL AND FOREIGN ENERGY SYSTEMS
- MODELING OF COMPUTER NETWORK WITH FAULT-TOLERANCE GATEWAY IN OMNET++
- PROTOTYPING OF ADAPTIVE USERs’ APPLICATION PROGRAMMING INTERFACES BY ARTIFICIAL INTELLIGENCE METHODS
- MODIFICATION METHOD OF SPACED REPETITION SEQUENCE BASED ON USER’S ONLINE ACTIVITY
- INTERACTIVE DEVICE FOR TOURIST VIEWPOINTS
- PATTERN RECOGNITION IN EXPERT DECISION-MAKING SYSTEMS
- INTERACTION WITH INTERNET OF THINGS DEVICES BY VOICE CONTROL
- NUMERICAL SOLUTION OF MULTIDIMENSIONAL THOMSON PROBLEM FOR VECTORS PACKAGING ON HYPERSPHERE IN BROADBAND RADIOCOMMUNICATION PROBLEMS
- ESTIMATION METHOD FOR LOGICAL DIFFICULTY AND STEREOTYPE OF OPERATORS’ ACTIVITY ALGORITHMS
- EVALUATION OF PARTS PRODUCTION QUALITY IN INSTRUMENT-MAKING
- RESEARCH OF FLEXURAL VIBRATIONS OF ROTATING SHAFTS WITH DISTRIBUTED INERTIAL, ELASTIC AND ECCENTRICITY PROPERTIES
- VIRTUAL INSTRUMENT FOR STUDY OF OPERATIONAL AMPLIFIERS BASED ON NI ELVIS PLATFORM
- SORPTION OF LEAD IONS FROM AQUEOUS SOLUTION ON MULTILAYER GRAPHENE