Roads are monitored via way of means of CCTV cameras passively i.e. expertise isn't always generated via way of means of the CCTV cameras. Human useful resource constraint i.e. there may be the very restricted posting of the visitor's police personnel at road crossings, highways, and far off places. In many cases, injuries are happened because of negligence via way of means of the pedestrian and being stranded in far-off places. Adding to this, even the bulk of human beings surrounding the coincidence scene are busy clicking photographs and videos ignorant of the truth that their little negligence should value a life. The photos are available to the government agencies after trouble has happened. To conquer this, we endorse a wise device that could employ the prevailing CCTV cameras with nighttime vision. The proposed device captures the video stream, computes the input, and the device signals are generated in real-time, because of this that no extra sensors could be required. Using the digital digicam itself, the plan is to discover injuries in real-time and additionally send signals to ambulances or firefighting services; in order that suitable assets wished for saving lives are to be had in time. In many cases, injuries are suggested as a result of negligence on the part of street customers and being stranded in remote locations. Furthermore, the vast majority of people in the vicinity of the accident scene are preoccupied with taking photographs and videos, oblivious to the fact that their inattention could cost a life. To overcome this, we recommend a clever gadget that can make use of existing CCTV cameras with night vision.

Keywords : Convolutional Neural Network, ResNet, Traffic net, openCV, LSTM, GPS, REST.