Various systems, methods and non-transitory computer-readable media are described, which may involve performing operations comprising: receiving, with an object detector, a first image from a first positional angle comprising a first perspective of a scene, receiving, with the object detector, a second image from a second, different positional angle comprising a second perspective of the scene, and performing, with the object detector, object detection on the first image from the first perspective and on the second image from the second perspective by cross-referencing data related to the first image and the second image within the object detector.