Image-based distance detection for non-zooming stationary camera towards detecting intrusive target

Early detection of hidden intents and potential for future attacks or offenses is the main goal of intelligence and warning systems. Distance measurement of intrusive targets is important for indoor monitoring based on the detected intrusion target image. Calculating the distance between the target and the camera can provide the basis for the computer to determine the closeness of the invasion and probably provide information for the security alarm system. Consequently, this paper presents an image-based distance detection system for a non-zooming stationary camera observing object of known height above the ground. The image coordinates of the corresponding foot and head points of the object were manually detected and the internal and external parameters of the camera used were obtained automatically on receiving the image. Simulation results show that satisfactory measurements could be obtained where the absolute mean errors value via the proposed approach lie within 5.5%.