Explicitly incorporating spatial information to recurrent networks for agriculture
This addresses the need for more accurate and robust vision systems in agriculture, though it is incremental as it builds on existing recurrent and convolutional networks.
The paper tackles the problem of improving classification in agricultural vision systems by explicitly incorporating spatial and temporal cues, resulting in absolute IoU improvements of 4.7% for crop-weed segmentation and 2.6% for fruit segmentation.
In agriculture, the majority of vision systems perform still image classification. Yet, recent work has highlighted the potential of spatial and temporal cues as a rich source of information to improve the classification performance. In this paper, we propose novel approaches to explicitly capture both spatial and temporal information to improve the classification of deep convolutional neural networks. We leverage available RGB-D images and robot odometry to perform inter-frame feature map spatial registration. This information is then fused within recurrent deep learnt models, to improve their accuracy and robustness. We demonstrate that this can considerably improve the classification performance with our best performing spatial-temporal model (ST-Atte) achieving absolute performance improvements for intersection-over-union (IoU[%]) of 4.7 for crop-weed segmentation and 2.6 for fruit (sweet pepper) segmentation. Furthermore, we show that these approaches are robust to variable framerates and odometry errors, which are frequently observed in real-world applications.