It is very challenging to detect traffic signs using a high-precision real-time approach in realistic scenes with respect to driver-assistance systems for driving vehicles and autonomous driving. To address this challenge, in this paper, a new detection scheme (named MSA_YOLOv3) is proposed to accurately achieve real-time localization and classification of small traffic signs. First, data augmentation is achieved using image mixup technology. Second, a multi-scale spatial pyramid pooling block is introduced into the Darknet53 network to enable the network to learn object features more comprehensively. Finally, a bottom-up augmented path is designed to enhance the feature pyramid in YOLOv3, and the result is to achieve accurate localization of objects by utilizing fine-grained features effectively in the lower layers. According to the tests on the TT100K dataset (which is a dataset for traffic sign detection), the performance of the proposed MSA_YOLOv3 is better than that of YOLOv3 in detecting small traffic signs. The detection speed of MSA_YOLOv3 is 23.81 FPS, and the mAP (mean Average Precision) reaches up to 86%.

Change detection approaches can detect changed areas of the same scene at different times. Hyperspectral remote-sensing images contain large amounts of spectral information at high resolution. As hyperspectral datasets become abundant, more and more change detection technologies use hyperspectral images as raw data. Hyperspectral images suffer from band redundancy. There is an urgent need to improve the directionality of change of information features. To solve these problems, in this article, we propose a CNN framework involving slow-fast band selection (SFBS) and feature fusion grouping (SFBS-FFGNET) for hyperspectral image change detection. The main contributions of this article are as follows: 1) based on slow feature analysis (SFA), an SFBS method is proposed, which selects slow and fast feature bands to better extract changed and unchanged features, to more effectively separate changed and unchanged pixels; 2) we used a difference matrix to enrich the level of change information to provide more change characteristics for change detection; and 3) an FFG method was used to generate a more discriminative feature group, and the related loss function was designed. Experimental results on multiple real hyperspectral datasets showed that SFBS can reduce the operating load on the computer and improve the accuracy of change detection, and FFG can also improve the accuracy of change detection. In summary, SFBS-FFGNET is superior to most existing change detection methods.

Summary: Genomic selection (GS) is a new breeding strategy. Generally, traditional methods are used for predicting traits based on the whole genome. However, the prediction accuracy of these models remains limited because they cannot fully reflect the intricate nonlinear interactions between genotypes and traits. Here, a novel single nucleotide polymorphism (SNP) feature extraction technique based on the Pearson‐Collinearity Selection (PCS) is firstly presented and improves prediction accuracy across several known models. Furthermore, gene network prediction model (NetGP) is a novel deep learning approach designed for phenotypic prediction. It utilizes transcriptomic dataset (Trans), genomic dataset (SNP) and multi‐omics dataset (Trans + SNP). The NetGP model demonstrated better performance compared to other models in genomic predictions, transcriptomic predictions and multi‐omics predictions. NetGP multi‐omics model performed better than independent genomic or transcriptomic prediction models. Prediction performance evaluations using several other plants' data showed good generalizability for NetGP. Taken together, our study not only offers a novel and effective tool for plant genomic selection but also points to new avenues for future plant breeding research.

Multitask sparse representation method improves the detection performance by constructing multiple associated sub-sparse representation tasks and jointly learning multiple sub-sparse representation tasks, and this method can make use of the spectral information. However, the using of spatial information needs to be improved. This paper designs a hyperspectral image target detection method which can both make use of spectral and spatial information, that is a weighted joint k-nearest neighbor and multitask learning sparse representation method (WJNN-MTL-SR) is proposed. This method mainly consists of the following steps:1) using multitask sparse representation to obtain the representation residuals. 2) weighted joint k-nearest neighbor is used into the joint region of test pixels to obtain the weighted joint Euclidean distance. 3) a decision function, combining the weighted joint Euclidean distance and residuals of the multitask sparse representation, is used to get target detection result. Experimental results demonstrate that the proposed method show better detection performance than state-of-the-art methods.