As one of the core modules of autonomous driving technology, environment perception has gradually become a hot research topic in industry and academia in recent years. However, self-driving vehicles face safety challenges due to the existence of perceptual blind spots and the lack of remote sensing capability. In this paper, a multi-modal fusion based on BEV representation for Vehicle-Infrastructure perception is proposed, referred to as V2I-BEVF, which mainly contains two branch networks for feature extraction from 2D images and 3D point clouds and transform them into BEV features, then use Deformable Attention Transformer to fuse and decode them in order to achieve high-precision real-time perception of road traffic participants. The V2I-BEVF algorithm proposed in this paper experimentally verified on the open-source roadside DAIR-V2X-I dataset from Tsinghua University and Baidu. The experimental results show that compared to several algorithm benchmarks provided by the DAIR-V2X-I dataset, the V2I-BEVF algorithm has a large improvement in pedestrian detection accuracy. Simultaneously, we verified the effectiveness of the proposed method on our collected dataset of roadside sensor devices. The V2I-BEVF algorithm can be combined with 5G/V2X communication technology and applied to V2I collaborative perception scenarios to take full advantage of wide roadside environmental perception vision and the small blind area.
Approximate nearest neighbor search (ANNS) is a fundamental problem in databases and data mining. A scalable ANNS algorithm should be both memory-efficient and fast. Some early graph-based approaches have shown attractive theoretical guarantees on search time complexity, but they all suffer from the problem of high indexing time complexity. Recently, some graph-based methods have been proposed to reduce indexing complexity by approximating the traditional graphs; these methods have achieved revolutionary performance on million-scale datasets. Yet, they still can not scale to billion-node databases. In this paper, to further improve the search-efficiency and scalability of graph-based methods, we start by introducing four aspects: (1) ensuring the connectivity of the graph; (2) lowering the average out-degree of the graph for fast traversal; (3) shortening the search path; and (4) reducing the index size. Then, we propose a novel graph structure called Monotonic Relative Neighborhood Graph (MRNG) which guarantees very low search complexity (close to logarithmic time). To further lower the indexing complexity and make it practical for billion-node ANNS problems, we propose a novel graph structure named Navigating Spreading-out Graph (NSG) by approximating the MRNG. The NSG takes the four aspects into account simultaneously. Extensive experiments show that NSG outperforms all the existing algorithms significantly. In addition, NSG shows superior performance in the E-commercial search scenario of Taobao (Alibaba Group) and has been integrated into their search engine at billion-node scale.
Aiming at the problem of excessive conservatism of traditional robust optimization in existing integrated energy microgrid planning, this paper proposes an integrated energy microgrid planning model based on robust chance constraints. Firstly, the typical architecture of the integrated energy microgrid is introduced. Secondly, an integrated energy microgrid planning model based on robust opportunity constraints is constructed. Thirdly, the complex opportunity constraints are transformed into the form of mixed integer linear programming through the Monte Carlo method. Finally, the effectiveness of the proposed model is verified through the comparison and analysis of actual calculation examples.
The current two-stage detectors remarkably benefit from hybrid representation of points and 3-D voxels, but they have high time cost and leave room for improving the accuracy of small objects. On the contrary, 2-D voxel-based methods tend to have good efficiency and better performance for small objects. An intuitive idea of optimizing a two-stage algorithm is to use a 2-D voxel-based backbone. However, naive representation substitution cannot achieve optimal joint learning of each representation and may cause a decrease in accuracy. In this article, we propose hybrid point–voxel RCNN (HPV-RCNN), a novel point cloud detection network which combines the merits of points and 2-D voxels. First, we propose a multiattentive voxel feature encoding module (MAVFE) to exploit multilevel attention of multiscale voxels. We also present a partial fusion pyramid network (PFPN) to effectively integrate multiresolution features and generate high-quality proposals. Then, a multiscale region of interest (RoI)-grid pooling (MSRGP) module is proposed to adaptively abstract proposal-specific features from sampled keypoints in multiple receptive fields. In addition, a cascade attentive module (CAM) is adopted to achieve incrementally proposal refinement by subsequent multiple subnetworks. Our method reaches top performance among two-stage methods in Cyclist and Pedestrian categories on the KITTI dataset while achieving real-time inference speed. Extensive experiments on challenging roadside DAIR-V2X-I dataset also demonstrate that our method achieves superior detection performance.
Neural Networks have achieved great success in many computer vision tasks, especially in image recognition. However, as neural networks grow deeper and deeper, to some extend, we've found them becoming difficult to train, and requiring samples in large scale dramatically, even with the help of Dropout and Dropconnect methods, which do improve the accuracy a bit but burdens the training process as a sacrifice. To overcome this, we propose a novel neuron connection model to generate dynamic graphs of computation. As synapses have two kinds: excitatory and inhibitory ones, our model also has two kinds of connections for neurons. In addition, we propose a training algorithm that deals with non-differentiable because the equations of the connections and activation function of neurons in our model are not really differentiable. To evaluate the effectiveness the proposed method, we apply it to the image recognition task, and the results show that our proposed model achieves state-of-the-art performance on three public datasets: MNIST, CIFAR-10, and CIFAR-100.
The oxide skin defect during hot rolling process for Cu-Ni-Si alloy strip was investigated. Oxide skin defects were analyzed by means of alloy elements detection and microstructures characterization. The characterization and test results showed that high temperature oxidation and silicon segregation are the main causes of the oxide skin defect. Pilot scale tests indicated that hot processing temperature for C70250 alloy should be lower than 950°C. Reducing atmosphere is recommended during the thermal treatment of Cu-Ni-Si alloys.
Cultivated peanut (Arachis hypogaea L.) is one of the most important oilseed crops worldwide. Pod-related traits, including pod length (PL), pod width (PW), ratio of PL to PW (PL/W) and 100-pod weight (100-PW), are crucial factors for pod yield and are key target traits for selection in peanut breeding. However, the studies on the natural variation and genetic mechanism of pod-related traits are not clear in peanut. In this study, we phenotyped 136 peanut accessions for four pod-related traits in two consecutive years and genotyped the population using a re-sequencing technique. Based on 884,737 high-quality single nucleotide polymorphisms (SNPs), genome-wide association studies (GWAS) were conducted for four pod-related traits using a fixed and random model uniform cyclic probability (FarmCPU) model. The results showed that a total of 36 SNPs were identified by GWAS, among which twenty-one, fourteen and one SNPs were significantly associated with PL, PL/W and 100-PW, respectively. The candidate regions where the four peak SNPs (10_76084075, 11_138356586, 16_64420451, and 18_126782541) were located were used for searching genes, and nineteen candidate genes for pod-related traits were preliminarily predicted based on functional annotations. In addition, we also compared the expression patterns of these nineteen candidate genes in different tissues of peanut, and we found that eight genes were specifically highly expressed in tender fruit, immature pericarp, or seed, so we considered these genes to be the potential candidate genes for pod-related traits. These results enriched the understanding of the genetic basis of pod-related traits and provided an important theoretical basis for subsequent gene cloning and marker-assisted selection (MAS) breeding in peanut.
The medicinal mushroom Inonotus obliquus has been a folk remedy for a long time in East-European and Asian countries. It has been ascribed to a number of triterpenoids that show various biological activities. In this study, the response surface methodology was employed to optimise the medium composition for triterpenoids production by I. obliquus in shake flask culture. A fractional factorial design was used to evaluate the effects of different components in the medium. Glucose, peptone, yeast powder, and CaCl2 were important factors significantly affecting I. obliquus triterpenoids production. These selected variables were subsequently optimised using steepest ascent method, a central composite design, and response surface methodology. The optimal medium composition was (% w/v): glucose, 5.92; peptone, 0.23; CaCl2, 0.048; yeast powder, 0.12; KH2PO4, 0.1; MgSO4, 0.02. Under optimal conditions, triterpenoids production by I. obliquus reached 5.51%, representing an increase of 1.4-fold compared with that using the basal medium (3.98%).
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)