The detection of traffic signs is easily affected by changes in the weather, partial occlusion, and light intensity, which increases the number of potential safety hazards in practical applications of autonomous driving. To address this issue, a new traffic sign dataset, namely the enhanced Tsinghua-Tencent 100K (TT100K) dataset, was constructed, which includes the number of difficult samples generated using various data augmentation strategies such as fog, snow, noise, occlusion, and blur. Meanwhile, a small traffic sign detection network for complex environments based on the framework of YOLOv5 (STC-YOLO) was constructed to be suitable for complex scenes. In this network, the down-sampling multiple was adjusted, and a small object detection layer was adopted to obtain and transmit richer and more discriminative small object features. Then, a feature extraction module combining a convolutional neural network (CNN) and multi-head attention was designed to break the limitations of ordinary convolution extraction to obtain a larger receptive field. Finally, the normalized Gaussian Wasserstein distance (NWD) metric was introduced to make up for the sensitivity of the intersection over union (IoU) loss to the location deviation of tiny objects in the regression loss function. A more accurate size of the anchor boxes for small objects was achieved using the K-means++ clustering algorithm. Experiments on 45 types of sign detection results on the enhanced TT100K dataset showed that the STC-YOLO algorithm outperformed YOLOv5 by 9.3% in the mean average precision (mAP), and the performance of STC-YOLO was comparable with that of the state-of-the-art methods on the public TT100K dataset and CSUST Chinese Traffic Sign Detection Benchmark (CCTSDB2021) dataset.

As the quality of life rises, the demand for flowers has increased significantly, leading to higher expectations for flower sorting system efficiency and speed. This paper presents a real-time, high-precision end-to-end method, which can complete three key tasks in the sorting system: flower localization, flower classification, and flower grading. In order to improve the challenging maturity detection, red–green–blue depth (RGBD) images were captured. The multi-task and multi-dimension-You Only Look Once (MTMD-YOLO) network was proposed to complete these three tasks in an end-to-end manner. The feature fusion was simplified to increase training speed, and the detection head and non-maximum suppression (NMS) were optimized for the dataset. This optimization allowed the loss function for the grading task to be added to train each task separately. The results showed that the use of RGBD and multi-task improved by 3.63% and 1.87% of mean average precision (mAP) on flower grading task, respectively. The final mAP of the flower classification and grading task reached 98.19% and 97.81%, respectively. The method also achieved real-time speed on embedded Jetson Orin NX, with 37 frames per second (FPS). This method provided essential technical support to determine the automatic flower picking times, in combination with a picking robot.

During the rice quality testing process, the precise segmentation and extraction of grain pixels is a key technique for accurately determining the quality of each seed. Due to the similar physical characteristics, small particles and dense distributions of rice seeds, properly analysing rice is a difficult problem in the field of target segmentation. In this paper, a network called SY-net, which consists of a feature extractor module, a feature pyramid fusion module, a prediction head module and a prototype mask generation module, is proposed for rice seed instance segmentation. In the feature extraction module, a transformer backbone is used to improve the ability of the network to learn rice seed features; in the pyramid fusion module and the prediction head module, a six-layer feature fusion network and a parallel prediction head structure are employed to enhance the utilization of feature information; and in the prototype mask generation module, a large feature map is used to generate high-quality masks. Training and testing were performed on two public datasets and one private rice seed dataset. The results showed that SY-net achieved a mean average precision (mAP) of 90.71% for the private rice seed dataset and an average precision (AP) of 16.5% with small targets in COCO2017. The network improved the efficiency of rice seed segmentation and showed excellent application prospects in performing rice seed quality testing.

Background: Mn doped ZnSe low dimensional materials are attractive for different biological labels, gene silencing and dilute-magnetic device. ZnSe clusters are one of the basic building blocks of quantum dots and even cluster-assembled nanodevices, stable structures of undoped ZnSe clusters were established by previous pioneering work, and the Mn doped ZnSe clusters had been investigated, but the stable clusters in the ferromagnetic state have not been found yet. Objective: Our work is mainly based on Mn doped clusters (Mn₂Zn₁₀Se₁₂) and C codoped clusters (Mn₂Zn₁₀Se₁₁) structure, magnetic properties through theoretical calculations. Methods: First principle density functional theory calculation with Dmol3 is used to execute all calculations. Results: Mn atoms prefer to substitute the nearest neighbor Zn atom sites in the rhombi part, and C atom prefers to occupy Se atom sites with shortest Mn-C bond length in Zn₁₂Se₁₂ nanocluster doping. Mn doped clusters (Mn₂Zn₁₀Se₁₂) are in antiferromagnetic states and the most stable C codoped clusters (Mn₂Zn₁₀Se₁₁) are in ferromagnetic states. Magnetic behavior localized at the 3d orbitals of transitional metal Mn, 4p orbital of atom Se and 2p orbital of C atom. Mn₂Zn₁₀Se₁₂ clusters are in antiferromagnetic states as the p-d hybridization introduced Mn-Mn superexchange mechanism. For the ferromagnetism of Mn₂Zn₁₀Se₁₂ nanocluster, hole mediated double exchange mechanism introduced by C atom p-d hole state hybridization has been suggested. Conclusion: The codoping of C atom can stabilize the ferromagnetism of clusters through hole mediated double exchange mechanism, which may be meaningful for the exploring materials for cluster- assembled spin-electronic devices.

Lowest energy structures of Zn_nSe_n (n=2–13) nanoclusters were obtained as the pristine clusters with first principle all-electron calculations. Second-order energy difference of the Lowest energy Zn_nSe_n (n=2–13) nanoclusters indicated that n=12 is the stable size. Then Zn₁₂Se₁₂ cluster were applied to be doped with single and two Fe atoms to investigate the structural and magnetic properties of Fe doped small ZnSe nanoclusters. Configuration of Fe doped Zn₁₂Se₁₂ were applied and total energy indicated that Fe atoms prefer to substitute Zn atoms in Fe-doped Zn₁₂Se₁₂ nanoclusters. And for the two Fe doped Zn₁₂Se₁₂ cluster, Fe atoms favor to locate at adjacent Zn atom sites in antiferromagnetic states because of the Fe–Fe short ranged superexchange mechanism, and energy gap between lowest unoccupied molecular orbital and the highest occupied molecular orbital were presented with Fe-Fe distance for the cluster with further light emitting exploring.