Abstract:
The increase of video surveillance systems has highlighted the interest in forensic anthropometric analysis of subjects who commit crimes and are captured by cameras during their criminal activities. There are different methodologies for human height estimation. Forensic researchers developed a methodological approach that allows the height of a subject to be estimated through a combined model of 3D laser scanning acquisition and video images acquired by video surveillance systems. The proposed study had highlighted three limits: not assessments had been made for image correction to limit the distortion effect, the method had been tested by only one laboratory and probably height assessment was dependent on the ergonomics. To overcome these limitations, in this paper the analysis was repeated by correcting the images to compare the new results obtained with the previous ones. Furthermore, the same methodological approach was applied by estimating the height of a mannequin, to limit the ergonomic effects, and proposing the same study to three different forensic laboratories to compare the results. The presented study demonstrates the reliability and repeatability of the system, as the results obtained by the three laboratories are very similar. They have obtained the same trend and the maximum estimate distance is approximately 6 cm. Furthermore, it has showed that the accuracy of results is dependent on image correction, which has little impact (approximately 1 cm more accurate on the corrected frame than the normal frame) on the height evaluation and they are not dependent to the ergonomics of the subject captured.
摘要:
视频监控系统的增加凸显了对犯罪并在犯罪活动中被摄像机捕获的受试者进行法医人体测量分析的兴趣。人类身高估计有不同的方法。法医研究人员开发了一种方法学方法,可以通过3D激光扫描采集和视频监控系统采集的视频图像的组合模型来估计受试者的身高。拟议的研究强调了三个限制:没有对图像校正进行评估以限制失真效应,该方法仅由一个实验室进行了测试,身高评估可能取决于人体工程学。为了克服这些限制,在本文中,通过校正图像来重复分析,以将获得的新结果与以前的结果进行比较。此外,同样的方法是通过估计人体模型的高度,为了限制人体工程学效果,并向三个不同的法医实验室提出相同的研究结果。提出的研究证明了系统的可靠性和可重复性,因为三个实验室获得的结果非常相似。他们获得了相同的趋势,最大估计距离约为6厘米。此外,它表明,结果的准确性取决于图像校正,这对高度评估几乎没有影响(在校正帧上比正常帧更精确大约1厘米),并且它们不依赖于所捕获的受试者的人体工程学。