A computer-implemented method, an automatic pest control monitoring system and computer program product automatically monitor for pests on crops. An autonomous vehicle equipped with a normal camera and at least one alternate camera, simultaneously captures a normal image and a true alternate image containing a same portion of the crops. A composite image is generated using the difference of the captured images. If at least one pest is determined to present by applying an object recognition algorithm to the composite image, reactive measures are automatically deployed. The alternate camera may be an infrared camera or an ultraviolet camera. The composite image is generated by correlating the normal image with the true alternate image, determining the differences between the normal image and the true alternate image, and generating the composite image based on the differences between the normal image and the true alternate image.
