Abstract: Systems and methods use cameras to provide autonomous navigation features. In one implementation, a traffic light detection system is disclosed. The system may include at least one image capture device configured to acquire a plurality of images of an area forward of the vehicle, the area including a traffic lamp fixture having at least one traffic light. At least one processing device may be configured to align areas of the plurality of images corresponding to the traffic light, based on a determined center of brightness, expand each pixel within the aligned areas, determine a set of average pixel values including an average pixel value for each set of corresponding expanded pixels within the aligned areas, and determine, based on the set of average pixel values, whether the traffic light includes an arrow.