The invention discloses a camera jelly effect detection method and
system based on
artificial intelligence, and the method comprises the steps: obtaining three-dimensional
point cloud data and RGB images of the same
visual angle and range, and obtaining a depth image according to the three-dimensional
point cloud data; dividing the three-dimensional
point cloud data into a plurality of sub-regions, and determining each candidate region I according to the sub-regions; finding out a depth region corresponding to the candidate region I in the depth image, and screening out a candidate region II from each depth region; dividing the depth image into M sub-block regions, and dividing the
RGB image into the same sub-block regions; calculating a total jelly effect quantitative index value according to the corresponding sub-block regions in the
RGB image and the depth image; and finally obtaining the jelly effect severity of the
RGB image. According to the invention, the three-dimensional point
cloud data and the RGB image are compared and analyzed to obtain an accurate and quantized jelly effect index, so that a reference basis is provided for the surveying and mapping process of the unmanned aerial vehicle, and the jelly effect judgment result of the image is more accurate.