Synthetically labeled images for maize plant detection in UAS images

Authors: PIYUSH, PANDEY - Orise Fellow; Best, Norman; Washburn, Jacob

Submitted to: Lecture Notes in Computer Science
Publication Type: Book / Chapter
Publication Acceptance Date: 8/28/2023
Publication Date: 12/1/2023
Citation: Piyush, P., Best, N.B., Washburn, J.D. 2023. Synthetically labeled images for maize plant detection in UAS images. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2023. Lecture Notes in Computer Science, vol 14361. Springer, Cham. p. 543–556.

Interpretive Summary: Not required

Technical Abstract: The detection of individual plants within field images is critical for many applications in precision agriculture and research. Computer vision models for object detection, while often highly accurate, require large amounts of labeled data for training, something that is not readily available for most plants. To address the challenge of creating large datasets with accurate labels, we used indoor images of maize plants to create synthetic field images with automatically derived bounding box labels, enabling the generation of thousands of synthetic images without any manual labeling. Training an object detection model (Faster R-CNN) exclusively on synthetic images led to a mean average precision (mAP) value of 0.533 when the model was evaluated on pre-processed real plot images. When fine-tuned with a small number of real plot images, the model pre-trained on the synthetic images (mAP = 0.884) outperformed the model that was not pre-trained.