Anomaly Detection for Agricultural Vehicles Using Autoencoders

The safe in-field operation of autonomous agricultural vehicles requires detecting all objects that pose a risk of collision. Current vision-based algorithms for object detection and classification are unable to detect unknown classes of objects. In this paper, the problem is posed as anomaly detection instead, where convolutional autoencoders are applied to identify any objects deviating from the normal pattern. Training an autoencoder network to reconstruct normal patterns in agricultural fields makes it possible to detect unknown objects by high reconstruction error. Basic autoencoder (AE), vector-quantized variational autoencoder (VQ-VAE), denoising autoencoder (DAE) and semisupervised autoencoder (SSAE) with a max-margin-inspired loss function are investigated and compared with a baseline object detector based on YOLOv5. Results indicate that SSAE with an area under the curve for precision/recall (PR AUC) of 0.9353 outperforms other autoencoder models and is comparable to an object detector with a PR AUC of 0.9794. Qualitative results show that SSAE is capable of detecting unknown objects, whereas the object detector is unable to do so and fails to identify known classes of objects in specific cases.

Automated summary

This study poses the object detection problem in autonomous agricultural vehicles as anomaly detection and applies convolutional autoencoders to identify objects that deviate from the normal pattern. The results show that the semisupervised autoencoder (SSAE) outperforms other autoencoder models in detecting unknown objects and is comparable to the YOLOv5-based object detector. Additionally, SSAE is capable of detecting unknown objects, whereas the object detector fails to do so.