A method, according to one example, includes receiving a 360-degree image that was captured by a 360-degree camera, converting the 360-degree image into a rectangular image, and copying an edge portion from a first edge of the rectangular image and pasting the copied edge portion to a second edge of the rectangular image, thereby forming a modified rectangular image. The method further includes applying a neural network to the modified rectangular image to identify objects appearing in the modified rectangular image, wherein the modified rectangular image facilitates object identification near the second edge.