Abstract: Proposed herein are an image detection device, a signal control system including the same, and a signal control method. The image detection device includes: a photographing unit configured to acquire an intersection image by capturing an image of an intersection; a control unit configured to generate detection information, including information about a vehicle-occupied or -unoccupied state for each of one or more detection channels set on the plane of the intersection by analyzing the intersection image acquired by the photographing unit; and a communication unit configured to transmit the detection information, generated by the control unit, to the traffic signal controller.

Abstract: Proposed herein are a signal control apparatus and method based on reinforcement learning. The signal control apparatus includes: a photographing unit configured to acquire an intersection image by capturing an image of an intersection; a control unit configured to calculate the congestion level information of the intersection by analyzing the intersection image acquired by the photographing unit, and to calculate control information for a subsequent signal by using a reinforcement learning model, trained by using state information calculated based on the congestion level of the intersection and reward information as input values, and the congestion level information; and a drive unit configured to drive traffic lights according to the control information for a subsequent signal calculated by the control unit.

Abstract: Proposed herein are a signal control apparatus and method. The signal control apparatus includes: a photographing unit configured to acquire a plurality of intersection images by capturing a plurality of intersections; a storage configured to store a program for the control of traffic signals; and a controller including at least one processor, and configured to calculate control information for the control of traffic lights at each of the plurality of intersections using the intersection images acquired through the photographing unit by executing the program. The controller calculates control information for the control of traffic lights at each of the plurality of intersections based on action information calculated by a plurality of agents by using a plurality of agents based on a reinforcement learning model trained by outputting action information for the control of traffic lights while using state information and a reward as input values.