Fig. 1. Coded markers. (a) Structure of coding; (b) scale of cross coding

Fig. 2. Detection flow of YOLO v3

Fig. 3. Bottleneck layer

Fig. 4. Transition layer

Fig. 5. Dense residual block

Fig. 6. Backbone network of improved YOLO v3

Fig. 7. False mark points

Fig. 8. Center positioning of coded points. (a) Target segmentation; (b) pretreatment; (c) centroid extraction; (d) center positioning

Fig. 9. Precision-Recall curves of model

Fig. 10. Comparison of detection effect of two experiments for the same photo. (a) Experiment 1; (b) experiment 1

Fig. 11. Test results in different environments

Fig. 12. Nearest distance comparison

Fig. 13. Influence of salt-and-pepper noise on recognition rate

Fig. 14. Influence of Gaussian noise on recognition rate

Fig. 15. Decoding results. (a) Poor condition; (b) good condition