Improved Convolutional Neural Network for Traffic Scene Segmentation

In actual traffic scenarios,precise recognition of traffic participants,such as vehicles and pedestrians,is crucial for intelligent transportation.This study proposes an improved algorithm built on Mask-RCNN to enhance the ability of autonomous driving systems to recognize traffic participants.The algorithmincorporates long and shortterm memory networks and the fused attention module(GSAM,GCT,and Spatial Attention Module)to enhance the algorithm’s capability to process both global and local information.Additionally,to increase the network’s initial operation stability,the original network activation function was replaced with Gaussian error linear unit.Experiments were conducted using the publicly available Cityscapes dataset.Comparing the test results,it was observed that the revised algorithmoutperformed the original algorithmin terms of AP_(50),AP_(75),and othermetrics by 8.7%and 9.6%for target detection and 12.5%and 13.3%for segmentation.

Image Semantic Segmentation for Autonomous Driving Based on Improved U-Net

Image semantic segmentation has become an essential part of autonomous driving.To further improve the generalization ability and the robustness of semantic segmentation algorithms,a lightweight algorithm network based on Squeeze-and-Excitation Attention Mechanism(SE)and Depthwise Separable Convolution(DSC)is designed.Meanwhile,Adam-GC,an Adam optimization algorithm based on Gradient Compression(GC),is proposed to improve the training speed,segmentation accuracy,generalization ability and stability of the algorithm network.To verify and compare the effectiveness of the algorithm network proposed in this paper,the trained networkmodel is used for experimental verification and comparative test on the Cityscapes semantic segmentation dataset.The validation and comparison results show that the overall segmentation results of the algorithmnetwork can achieve 78.02%MIoU on Cityscapes validation set,which is better than the basic algorithm network and the other latest semantic segmentation algorithms network.Besides meeting the stability and accuracy requirements,it has a particular significance for the development of image semantic segmentation.

Recoloring tomato fruit by CRISPR/Cas9-mediated multiplex gene editing

Fruit color is an important horticultural trait,which greatly affects consumer preferences.In tomato,fruit color is determined by the accumulation of different pigments,such as carotenoids in the pericarp and f lavonoids in the peel,along with the degradation of chlorophyll during fruit ripening.Since fruit color is a multigenic trait,it takes years to introgress all color-related genes in a single genetic background via traditional crossbreeding,and the avoidance of linkage drag during this process is difficult.Here,we proposed a rapid breeding strategy to generate tomato lines with different colored fruits from red-fruited materials by CRISPR/Cas9-mediated multiplex gene editing of three fruit color-related genes(PSY1,MYB12,and SGR1).Using this strategy,the red-fruited cultivar‘Ailsa Craig’has been engineered to a series of tomato genotypes with different fruit colors,including yellow,brown,pink,light-yellow,pink-brown,yellow-green,and light green.Compared with traditional crossbreeding,this strategy requires less time and can obtain transgene-free plants with different colored fruits in less than 1 year.Most importantly,it does not alter other important agronomic traits,like yield and fruit quality.Our strategy has great practical potential for tomato breeding and serves as a reference for improving multigene-controlled traits of horticultural crops.

Traffic Flow Statistics Method Based on Deep Learning and Multi-Feature Fusion

Traffic flow statistics have become a particularly important part of intelligent transportation.To solve the problems of low real-time robustness and accuracy in traffic flow statistics.In the DeepSort tracking algorithm,the Kalman filter(KF),which is only suitable for linear problems,is replaced by the extended Kalman filter(EKF),which can effectively solve nonlinear problems and integrate the Histogram of Oriented Gradient(HOG)of the target.The multi-target tracking framework was constructed with YOLO V5 target detection algorithm.An efficient and longrunning Traffic Flow Statistical framework(TFSF)is established based on the tracking framework.Virtual lines are set up to record the movement direction of vehicles to more accurate and detailed statistics of traffic flow.In order to verify the robustness and accuracy of the traffic flow statistical framework,the traffic flow in different scenes of actual road conditions was collected for verification.The experimental validation shows that the accuracy of the traffic statistics framework reaches more than 93%,and the running speed under the detection data set in this paper is 32.7FPS,which can meet the real-time requirements and has a particular significance for the development of intelligent transportation.

Tomato CYP94C1 inactivates bioactive JA-lle to attenuate jasmonate-mediated defense during fruit ripening

Dear Editor,Fruit rot caused by necrotrophic pathogens results in substantial reductions in fruit yield and revenues worldwide(Petrasch et al.,2019).A widespread phenomenon in fleshy fruit species is the susceptibility of ripe fruits to necrotrophs(Silva et al.,2021),which facilitates seed dispersal(Forlani et al.,2019)but causes severe post-harvest losses in production.As most of the nutritional and sensory qualities of fruits are elaborated at the ripening stage(Liu et al.,2015),balancing fruit ripening and pathogen resistance to maintain fruit quality has proven to be challenging.A deeper understanding of the mechanisms underlying the increased susceptibility of fruits to necrotrophs during ripening could lead to new strategies for producing necrotrophy-resistant fruits without compromising ripening-relatedquality.

A Transcriptional Network Promotes Anthocyanin Biosynthesis in Tomato Flesh

Dietary anthocyanins are important health-promoting antioxidants that make a major contribution to the quality of fruits. It is intriguing that most tomato cultivars do not produce anthocyanins in fruit. However, the purple tomato variety Indigo Rose, which has the dominant Aft locus combined with the recessive atv locus from wild tomato species, exhibits light-dependent anthocyanin accumulation in the fruit skin. Here, we report that Aft encodes a functional anthocyanin activator named SlAN2-like, while atv encodes a nonfunctional version of the anthocyanin repressor SlMYBATV. The expression of SlAN2-like is responsive to light, and the functional SlAN2-like can activate the expression of both anthocyanin biosynthetic genes and their regulatory genes, suggesting that SlAN2-like acts as a master regulator in the activation of anthocyanin biosynthesis. We further showed that cultivated tomatoes contain nonfunctional alleles of SlAN2-like and therefore fail to produce anthocyanins. Consistently, expression of a functional SlAN2-like gene driven by the fruit-specific promoter in a tomato cultivar led to the activation of the entire anthocyanin biosynthesis pathway and high-level accumulation of anthocyanins in both the peel and flesh. Taken together, our study exemplifies that efficient engineering of complex metabolic pathways could be achieved through tissue-specific expression of master transcriptional regulators.

Efficient generation of pink-fruited tomatoes using CRISPR/Cas9 system

Tomato （Solanum lycopersicum） is the leading vegetable crop worldwide and an essential component of a healthy diet （Lin et al., 2014; Du et al., 2017）. Fruit color is regarded as one of the most important commercial traits in tomato （The Tomato Genome Consortium, 2012）. Consumers in different regions have different color preferences. For example, European and American consumers prefer red tomatoes, while pink tomatoes are more pop- ular in Asia countries, particularly in China and Japan （Ballester et al., 2010; Lin et al., 2014）. However, most of tomato breeding ma- terials are red-fruited, thus the generation of pink-fruited materials is very important for Asian tomato production. Metabolomics and genetics studies demonstrate that the pink trait results from the absence of yellow-colored flavonoid naringenin chalcone （NarCh） in the peels,

Mediator complex subunit MED25 physically interacts with DST to regulate spikelet number in rice

Grain number is a flexible trait and contributes significantly to grain yield.In rice,the zinc finger transcription factor DROUGHT AND SALT TOLERANCE(DST)controls grain number by directly regulating cytokinin oxidase!dehydrogenase 2(OsCKX2)expression.Although specific upstream regulators of the DST-OsCKX2 module have been identified,the mechanism employed by DST to regulate the expression of OsCKX2 remains unclear.Here,we demonstrate that DST-interacting protein 1(DIP1),known as Mediator subunit OsMED25,acts as an interacting coactivator of DST.Phenotypic analyses revealed that OsMED25-RNAi and the osmed25 mutant plants exhibited enlarged panicles,with enhanced branching and spikelet number,similar to the dst mutant.Genetic analysis indicated that OsMED25 acts in the same pathway as the DST-OsCKX2 module to regulate spikelet number per panicle.Further biochemical analysis showed that OsMED25 physically interacts with DST at the promoter region of OsCKX2,and then recruits RNA polymerase II(Pol II)to activate OsCKX2 transcription.Thus,OsMED25 was involved in the communication between DST and Pol II general transcriptional machinery to regulate spikelet number.In general,our findings reveal a novel function of OsMED25 in DST-OsCKX2 modulated transcriptional regulation,thus enhancing our un derstanding of the regulatory mechanism underlying DST-OsCKX2-mediated spikelet number.