FLIR ATR using location uncertainty

Liu, Gang; Haralick, Robert M.

doi:10.1117/1.482738

Cited by 5 publications

(2 citation statements)

References 36 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research has continued on improved ATRs, in some cases exploiting the spectral characteristics of the targets, 3 in others employing different signal-processing algorithms. [4][5][6] However, at the present time, ATRs remain imperfect and can be used only as automated aids, with the human making the final decision to acquire a target.…”

Section: Introductionmentioning

confidence: 99%

Modeling the efficacy of automated aids in target acquisition under conditions of heavy workload

Maltz

2005

Opt. Eng

View full text Add to dashboard Cite

Target acquisition tasks are often augmented by automated aids to advise human observers during the detection process. The question arises whether these automated aids, by nature imperfect, should be implemented under all conditions. This study examines the efficacy of an imperfect automated aid in human target acquisition performance under conditions of high mental workload. Human observers performed a target acquisition task aided by an automated aid ͑cuer͒ of varying accuracy concurrently with a military tracking task. Results indicate that the automated aid can improve performance over the unaided condition when it is highly reliable. Evidence of dependence on the system by the observers was found. The thesis here is that the condition of high mental workload induced greater acceptance of and reliance on the automated aid by the observers, which manifested in the highly significant cue dependence results. Another element found in the observers' interaction with the automated aid, which could be a consequence of overreliance, was a high perceived reliability of the cuer, which led observers to respond more confidently to cued targets. These results can help increase the understanding of human behavior vis-à-vis working with automated aids when under conditions of high mental workload.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling the efficacy of automated aids in target acquisition under conditions of heavy workload

Maltz

2005

Opt. Eng

View full text Add to dashboard Cite

show abstract

“…The performance is improved by a Bayesian classifier based algorithm [6] using eight input features. The performance is further improved recently by the introduction of the centroid uncertainty feature [7,8] to Bayesian classifier. These algorithms are designed to detect target vehicles which meet certain size and orientation specifications.…”

Section: Vehicle Detection Performancementioning

confidence: 99%

Vehicle ground-truth database for the vertical-view Ft. Hood imagery

Liu

Haralick²

Proceedings 15th International Conference on Pattern Recognition. ICPR-2000

View full text Add to dashboard Cite

This paper reports the work on building the ground-truth databases for the vehicles in the vertical-view Ft. Hood (VVFH) image data set. We briefly describe the protocols followed in manual annotation of the images, how the ground-truth information is inferred from the annotated image data, and the major entities in the ground-truth database. The vehicle detection performance of a few algorithms is evaluated using the data set. The entire data set of images and ground-truth is available on the Internet.

show abstract