Presentation 2007-02-23
Tracking Performance Evaluation of N-back Scan MHT
Yasushi OBATA, Masayoshi ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) MHT(Multiple Hypothesis Tracking) is well-known tracking algorithm for its association performance in dense environment. In MHT hypotheses are reduced by calculating probability and select upper hypotheses in a usual way. Regardless of computational load, better association performance can be expected by using N-back scan, maintaining all hypotheses in N-scan and select one hypothesis in past over N-scan, for hypotheses reduction. The N-back scan MHT is similar to MFA(Multiple Frame Assignment), which attracts much attention as an advanced method. We evaluate the performance of the N-back scan MHT, by simulation of track initiation in clutter environment and track maintenance of low observable target. From the result of simulation, we can predict that MFA shows better performance than MHT. For example, former success rate of tracking a maneuvering target, is 30 points better than latter.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) MHT / MFA / Association / N-back Scan
Paper # SANE2006-142
Date of Issue

Conference Information
Committee SANE
Conference Date 2007/2/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Space, Aeronautical and Navigational Electronics (SANE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Tracking Performance Evaluation of N-back Scan MHT
Sub Title (in English)
Keyword(1) MHT
Keyword(2) MFA
Keyword(3) Association
Keyword(4) N-back Scan
1st Author's Name Yasushi OBATA
1st Author's Affiliation Mitsubishi Electric Corporation()
2nd Author's Name Masayoshi ITO
2nd Author's Affiliation Mitsubishi Electric Corporation
Date 2007-02-23
Paper # SANE2006-142
Volume (vol) vol.106
Number (no) 542
Page pp.pp.-
#Pages 6
Date of Issue