• Laser & Optoelectronics Progress
  • Vol. 57, Issue 24, 241005 (2020)
Bo Zhang1、* and Gang Liu1、2
Author Affiliations
  • 1College of Information Science and Engineering, Changsha Normal University, Changsha, Hunan 410100, China
  • 2Physical Science and Electronics, Central South University, Changsha, Hunan 410083, China
  • show less
    DOI: 10.3788/LOP57.241005 Cite this Article Set citation alerts
    Bo Zhang, Gang Liu. Research on Target Tracking Algorithm Based on Similarity Feature Estimation[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241005 Copy Citation Text show less
    Neighborhood method
    Fig. 1. Neighborhood method
    Specific method for selecting specific search area
    Fig. 2. Specific method for selecting specific search area
    Tracking results of target tracking algorithm based on similarity feature estimation
    Fig. 3. Tracking results of target tracking algorithm based on similarity feature estimation
    Performance comparison of different target tracking algorithms, under the experimental scene of enlarged target size
    Fig. 4. Performance comparison of different target tracking algorithms, under the experimental scene of enlarged target size
    Performance comparison of different target tracking algorithms, under the experimental scene of reduced target size
    Fig. 5. Performance comparison of different target tracking algorithms, under the experimental scene of reduced target size
    SNR comparison of output results with different target tracking algorithms
    Fig. 6. SNR comparison of output results with different target tracking algorithms
    No.ConfigurationtypeSpecificconfigurationConfigurationdata
    1Hardware partCPUIntel Core 2
    Frequency/GHz1.2
    RAM/G2
    2Software partOperating systemXP
    Development tools2015 VS platform
    Table 1. Specific configuration data of the experimental environment
    No.Configuration typeConfiguration data
    1Coding classHigh class
    2Image tracking size4CIF、CIF
    3Encoding bandwidth/k2048、1024、768、384
    4Coding format4MPEG
    5Reference codeXVID reference software
    6Code specific bit rate1024
    7Encode the specificframe rate/(frame/s)25
    Table 2. Specific configuration data of video coding in the experiment
    No.Configuration typeConfiguration data
    1Color space configurationHSV space
    2Component configurationH component
    3Quantization treatment series32
    4Kernel functionEpanachnekov
    Table 3. Parameter specific configuration data
    ScenarioEnlarge the target sizeexperiment sceneReduce the target size of theexperimental scene
    Track target number135135
    Target tracking algorithm based onsalient features/ns623789817626749860
    Algorithm based on fusionfeatures/ns571577634524581612
    Algorithm based on backgroundweighting/ns597682701582654693
    Algorithm based on convolutionalnetwork/ns412421430461487496
    Target tracking algorithm based on kernelcorrelation filtering of dual feature model/ns532597631624636675
    Algorithm based on similarityfeature estimation/ns245344435267355430
    Table 4. Time-consuming comparison of target tracking process with different algorithms
    Bo Zhang, Gang Liu. Research on Target Tracking Algorithm Based on Similarity Feature Estimation[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241005
    Download Citation