Abstract
Taxicab security cameras are widely used to deter crimes against taxicab drivers in two-row-seating taxicabs. Some of these cameras have difficulty for use in three-row-seating taxicabs due to increased distance between the camera and the third-row seats. This project tested five sample taxicab security cameras with different image-sensor pixel counts to determine their utility for three-row-seating taxicabs. The cameras videotaped a normalized camera resolution test chart mounted in the third-row seat of a simulated three-row-seating taxicab in both daylight and dark (with infrared radiation) conditions. The resolution of each camera was measured and compared with the resolution threshold for customer facial identification. A dome-mounted camera with a standard-definition image-sensor is suggested as an effective camera in sustaining high camera resolution with small data file size for facial identification in the third-row seats. The image-sensors with at least 1280 × 720 pixels are suggested for windshield-mounted cameras in three-row-seating taxicabs for facial identification.
Acknowledgements
The author would like to thank Mr Bradley Newbraugh and Ms Darlene Weaver for their assistance in experiment preparation and data collection. The author would like to thank Mr Nelson Barros and Dr Ian Radbone for their external peer reviews, and Dr Stephen Martin for his internal peer review. The author would also like to thank Mr James Green, Dr Hongwei Hsiao, Dr Tony McKenzie, Mr Frank Palya and Mr Timothy Pizatella for their internal reviews.
Disclaimers
The findings and conclusions in this report are those of the author and do not necessarily represent the official position of the National Institute for Occupational Safety and Health (NIOSH), Centers for Disease Control and Prevention. Mention of company names or products does not imply endorsement by the NIOSH.
Disclosure statement
No potential conflict of interest was reported by the author.