Use of vehicle signature analysis and lexicographic optimization for vehicle reidentification on freeways

Sun, Carlos; Ritchie, Stephen G.; Tsai, Kevin; Jayakrishnan, R.

doi:10.1016/s0968-090x(99)00018-2

Cited by 91 publications

(45 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results Table II show fusion weights for four features instead of the six that we describe, because the weights pertaining to the maximum inductive amplitude feature and the electronic length feature had values of zero on the training set we used. These two features are kept in the general formulation in Section IV, because based on previous experience they could contribute significantly if another data set were used (see [4]). Table II shows several valuable results.…”

Section: Resultsmentioning

confidence: 99%

“…Vehicle reidentification can be accomplished by matching individual vehicles or platoons (groups) of vehicles. Some algorithms match individual inductive loop signatures from vehicles by correlating such signatures from two contiguous sites [4], [15]. One traditional method of vehicle reidentification is license plate matching [16].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Fusion of the six features is performed to get an overall fusion distance given by (4) where is the fusion weight applied to the vehicle signature distance, is the fusion weight applied to the color information feature distance, is the fusion weight applied to the velocity feature distance, is the fusion weight applied to the maximum inductive amplitude feature distance, is the fusion weight applied to the electronic length feature distance, and is the fusion weight applied to the platoon traversal time feature distance. As before, the subscripts and refer to upstream and downstream, respectively.…”

Section: Fusion and Classification Approachmentioning

confidence: 99%

See 2 more Smart Citations

Vehicle Reidentification Using Multidetector Fusion

Sun

Arr

Ramachandran

et al. 2004

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Abstract-Vehicle reidentification is the process of matching vehicles from one point on the roadway (one field of view) to the next. By performing vehicle reidentification, important traffic parameters including travel time, travel time variability, section density, and partial dynamic origin/destination demands can be obtained. Field traffic data were collected in Alton Parkway in Southern California for training and testing of the multidetector vehicle reidentification algorithm. These data consisted of inductive loop signatures of vehicles that traversed two detector stations spanning a section of an arterial and the corresponding video of these signatures. Even though the video collected was not optimized for pattern-recognition purposes, an investigation into the feasibility of fusing inductive vehicle signatures with video for anonymous vehicle reidentification was conducted. The resulting reidentification rate of over 90% shows that this approach merits further investigation. The results also show that the use of detector fusion provides system redundancy and yields slightly better results than the use of a single detector.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Fusion and Classification Approachmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle Reidentification Using Multidetector Fusion

Sun

Arr

Ramachandran

et al. 2004

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…A freeway control system using a dynamic traffic flow model and vehicle reidentification technique is the subject of [7]. A lexicographical optimization for vehicle reidentification on freeways is discussed in [8] for which a 78% accuracy is obtained. The reidentification accuracy is the number of vehicles identified correctly divided by the total number of vehicles assessed and is expressed as a percent.…”

Section: Introductionmentioning

confidence: 99%

“…The reidentification accuracy is the number of vehicles identified correctly divided by the total number of vehicles assessed and is expressed as a percent. The approach in [8] performs reidentification by matching individual vehicles. A recent algorithm [9] uses the fact that vehicles tend to travel in groups or platoons to improve accuracy.…”

Section: Introductionmentioning

confidence: 99%

Fusion of wavelet transform and color information features for automatic vehicle reidentification in intelligent transportation systems

Arr

Sun

Ramachandran

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing

View full text Add to dashboard Cite

Vehicle reidentification is the process of reidentifying or tracking vehicles from one point on the roadway to the next. By performing vehicle reidentification, important traffic parameters including travel time, section density and partial dynamic origin/destination demands can be obtained. This provides for anonymous tracking of vehicles from site-to-site and has the potential for improving Intelligent Transportation Systems (ITS) by providing more accurate data. This paper presents a fusion based vehicle reidentification algorithm that uses four different features, namely, (1) the wavelet transform of the inductive signature vector acquired from loop detectors, (2) vehicle velocity, (3) traversal time and (4) color information (based on images acquired from video cameras) to achieve high accuracy. A nearest neighbor approach classifies the features and linear feature fusion is shown to improve performance. With the fusion of four features, more than a 92 percent accuracy is obtained on real data collected from a parkway in California. Also, it is found that the wavelet transform improves performance and reduces the dimension of the feature vector when compared to the raw vehicle signatures.

show abstract