Detecting Wheat Heads from UAV Low-Altitude Remote Sensing Images Using Deep Learning Based on Transformer

Abstract

The object detection method based on deep learning convolutional neural network (CNN) significantly improves the detection performance of wheat head on wheat images obtained from the near ground. Nevertheless, for wheat head images of different stages, high density, and overlaps captured by the aerial-scale unmanned aerial vehicle (UAV), the existing deep learning-based object detection methods often have poor detection effects. Since the receptive field of CNN is usually small, it is not conducive to capture global features. The visual Transformer can capture the global information of an image; hence we introduce Transformer to improve the detection effect and reduce the computation of the network. Three object detection networks based on Transformer are designed and developed, including the two-stage method FR-Transformer and the one-stage methods R-Transformer and Y-Transformer. Compared with various other prevalent object detection CNN methods, our FR-Transformer method outperforms them by 88.3% for AP50 and 38.5% for AP75. The experiments represent that the FR-Transformer method can gratify requirements of rapid and precise detection of wheat heads by the UAV in the field to a certain extent. These more relevant and direct information provide a reliable reference for further estimation of wheat yield.

Implementation of a Bio-Inspired Neural Architecture for Autonomous Vehicles on a Multi-FPGA Platform

“…Overall, a growing autonomous vehicle market needs to implement tasks such as visual navigation, object detection, etc. Hence, a broad summary with various software and hardware-based implementations, running on CPU, GPU and/or FPGAs, is detailed in various surveys [ 43 , 44 , 45 , 46 , 47 ].…”

A Survey of Object Detection for UAVs Based on Deep Learning

“…Small objects R-DFPN [84] Google Earth 2018 Ship RSOD [85] UAVDT [68] 2022 Traffic Complex background SCRDet [86] DOTA [64] 2019 Multicategory Shao et al [87] UAV-head [87] 2021 Pedestrian FR-Transformer [88] UWHD [88] 2022 Agriculture Category imbalance Deng et al [14] NWPU VHR-10 [89] 2018 Multicategory MLD [90] Leaf [90] 2022 Agriculture…”

“…However, traditional attention mechanisms are typically built on CNN architectures and only calculate the weights of certain regions. To better capture more global context information and improve the accuracy of UAV image object detection, Zhu et al [88] combined transformer with convolutional kernel attention mechanism and proposed the FR-transformer method to achieve the requirement of accurate and fast detection for wheat heads by UAVs. Figure 15 shows the network structure of FR-transformer.…”

“…Figure 16 shows the qualitative results of the method in [88] and Table 7 shows the detection performance of the FR-transformer method. According to the results of the wheat detection task, the FR-transformer method can detect wheat heads with high accuracy in the real field environment.…”

Research on optical slit setting technique of off-axis triple reflection imaging spectrometer

“…For example, the Resonon-PIKA II imaging spectrometer developed by Idaho National Laboratory in the United States has a working band of 396.3 ~ 892.1 nm, a spectral resolution of 6.2 nm and a mass of 1.043 kg [7] . The S185 airborne spectrometer developed by Cubert in Germany has a working band of 450 ~ 950 nm, a spectral resolution of 8 nm and a mass of 0.49 kg [8] . Wu Zhenzhou et al from the University of Science and Technology of China developed a miniature offner imaging spectrometer for crop growth monitoring, with a working band of 400 ~ 1000 nm, a spectral resolution of 4 nm and a mass of 5 kg [6] .…”