Crystallization is important to the pharmaceutical, the chemical, and the materials fields, where the morphology of crystals is one of the key factors affecting the quality of crystallization. High-throughput screening based on microfluidic droplets is a potent technique to accelerate the discovery and development of new crystal morphologies with active pharmaceutical ingredients. However, massive crystal morphologies’ datum needs to be identified completely and accurately, which is time-consuming and labor-intensive. Therefore, effective morphologies’ detection and small-target tracking are essential for high-efficiency experiments. In this paper, a new improved algorithm YOLOv8 (YOLO-PBESW) for detecting indomethacin crystals with different morphologies is proposed. We enhanced its capability in detecting small targets through the integration of a high-resolution feature layer P2, and the adoption of a BiFPN structure. Additionally, in this paper, adding the EMA mechanism before the P2 detection head was implemented to improve network attention towards global features. Furthermore, we utilized SimSPPF to replace SPPF to mitigate computational costs and reduce inference time. Lastly, the CIoU loss function was substituted with WIoUv3 to improve detection performance. The experimental findings indicate that the enhanced YOLOv8 model attained advancements, achieving AP metrics of 93.3%, 77.6%, 80.2%, and 99.5% for crystal wire, crystal rod, crystal sheet, and jelly-like phases, respectively. The model also achieved a precision of 85.2%, a recall of 83.8%, and an F1 score of 84.5%, with a mAP of 87.6%. In terms of computational efficiency, the model’s dimensions and operational efficiency are reported as 5.46 MB, and it took 12.89 ms to process each image with a speed of 77.52 FPS. Compared with state-of-the-art lightweight small object detection models such as the FFCA-YOLO series, our proposed YOLO-PBESW model achieved improvements in detecting indomethacin crystal morphologies, particularly for crystal sheets and crystal rods. The model demonstrated AP values that exceeded L-FFCA-YOLO by 7.4% for crystal sheets and 3.9% for crystal rods, while also delivering a superior F1-score. Furthermore, YOLO-PBESW maintained a lower computational complexity, with parameters of only 11.8 GFLOPs and 2.65 M, and achieved a higher FPS. These outcomes collectively demonstrate that our method achieved a balance between precision and computational speed.

As a typical intelligent agricultural equipment, the harvesting robot integrates various advanced technologies such as robotic, recognition and control. Because of the need the complexity of agricultural scenes, the major bottleneck restricting the performance of harvesting robots is the accuracy of the detection system. In this paper, we proposed a method for navel orange recognition based on the attention mechanism the selection of detection frames. Firstly, the attention mechanism module was incorporated into the feature extraction network to obtain important features. Then, the overlapping area and centroid distance between the target frame and detection frame were considered. And DIoU-NMS was used instead of NMS to improve the localization accuracy. Finally, a dataset based on navel oranges has been collected, with a total sample size of 811 images. The training-set and dataset have been randomly differentiated according to 4:1. The results showed that the improved YOLOv5 research algorithm can obtain 99.4% average accuracy, which is a 7.4% improvement compared to the YOLOv51 algorithm. The new improved YOLOv5 algorithm provided a more accurate and faster method for the navel orange detection.