NightHawk NVS is an, in-car camera night vision system that aids drivers in locating obstacles, road signs, and other dangers at night. The system consists of an externally mounted front-facing camera, a processing unit that constantly analyzes each frame for potential dangers, and a touchscreen user interface system. This system uses a series of cutting edge image processing and artificial intelligence algorithms to determine whether individual objects in an image represent a threat to the vehicle. The system is aware of its surroundings and can determine different kinds of dangers in a wide range of situations. When analyzing its surroundings, the system attempts to locate objects that have a high likelihood of entering the vehicle’s path. When searching for obstacles, the system runs the frame through a Neural Net to see if any people, animals, or obstacles are in the vehicle’s path. The system locates and marks common road signs and informs the driver of them. To find signs, the system uses advanced template matching algorithms and techniques to provide highly accurate results and minimize false positive detections. The system also locates lanes on the road and alerts the driver if the vehicle is not within lane boundaries. The lane detection uses thresholding and contour mapping to provide reliable and accurate highlighting of the lanes. The techniques utilized in the system allow it to run in real-time up to 30fps and yield higher accuracies than other prototype night vision systems for cars.
Senior Design Project
NightHawk NVS is an, in-car camera night vision system that aids drivers in locating obstacles, road signs, and other dangers at night. The system consists of an externally mounted front-facing camera, a processing unit that constantly analyzes each frame for potential dangers, and a touchscreen user interface system. This system uses a series of cutting edge image processing and artificial intelligence algorithms to determine whether individual objects in an image represent a threat to the vehicle. The system is aware of its surroundings and can determine different kinds of dangers in a wide range of situations. When analyzing its surroundings, the system attempts to locate objects that have a high likelihood of entering the vehicle’s path. When searching for obstacles, the system runs the frame through a Neural Net to see if any people, animals, or obstacles are in the vehicle’s path. The system locates and marks common road signs and informs the driver of them. To find signs, the system uses advanced template matching algorithms and techniques to provide highly accurate results and minimize false positive detections. The system also locates lanes on the road and alerts the driver if the vehicle is not within lane boundaries. The lane detection uses thresholding and contour mapping to provide reliable and accurate highlighting of the lanes. The techniques utilized in the system allow it to run in real-time up to 30fps and yield higher accuracies than other prototype night vision systems for cars.
http://www.bu.edu/today/node/11275
Video