Feature Constraints Research Articles

D3L-SLAM: A Comprehensive Hybrid Simultaneous Location and Mapping System with Deep Keypoint, Deep Depth, Deep Pose, and Line Detection

Robust localization and mapping are crucial for autonomous systems, but traditional handcrafted feature-based visual SLAM often struggles in challenging, textureless environments. Additionally, monocular SLAM lacks scale-aware depth perception, making accurate scene scale estimation difficult. To address these issues, we propose D3L-SLAM, a novel monocular SLAM system that integrates deep keypoints, deep depth estimates, deep pose priors, and a line detector. By leveraging deep keypoints, which are more resilient to lighting variations, our system improves the robustness of visual SLAM. We further enhance perception in low-texture areas by incorporating line features in the front-end and mitigate scale degradation with learned depth estimates. Additionally, point-line feature constraints optimize pose estimation and mapping through a tightly coupled point-line bundle adjustment (BA). The learned pose estimates refine the feature matching process during tracking, leading to more accurate localization and mapping. Experimental results on public and self-collected datasets show that D3L-SLAM significantly outperforms both traditional and learning-based visual SLAM methods in localization accuracy.

A LiDAR SLAM Algorithm Considering Dynamic Extraction of Feature Points in Underground Coal Mine

Abstract. To address the absence of GNSS signals in underground coal mines and the susceptibility of mainstream LiDAR SLAM to degradation due to insufficient feature constraints, this paper proposes a tightly-coupled SLAM algorithm incorporating LiDAR and IMU for use in such environments. The paper initially introduces a dynamic feature point extraction strategy, where the number of corner feature points can be dynamically adjusted based on the occurrence of degradation in the underground coal mine environment. This approach constructs a constraint matrix with rich and robust feature information, enhancing pose estimation accuracy in environments with inadequate feature constraints, mitigating degradation effects, and reducing global cumulative error. Subsequently, the consistent building of the underground coal mine environment is achieved through back-end factor graph optimization. Finally, to validate the effectiveness of the method, experimental analysis is conducted in an underground coal mine. The results demonstrate that LeGO_LOAM exhibits poor robustness in underground coal mines and fails to construct a globally consistent pose estimation and map. Conversely, the pose estimation error of the proposed method in this paper is 50.93% lower in the plane direction and 42.13% lower in the elevation direction compared to LIO_SAM. This underscores the method's significance as crucial technical support for the intelligent perception and positioning of robots in underground coal mines.

Surrogate-model-based low-carbon optimization method for tolerance allocation of mechanical components under bidirectional constraints

The low-carbon optimization of tolerance allocation involves reducing production costs and carbon emissions, while ensuring dimensional precision, making it a crucial pathway to achieving low-carbon manufacturing. However, the complex mapping mechanism between tolerance, cost, and carbon emissions makes it challenging to construct effective mechanistic models. This complexity arises from both the forward constraints of multiple-coupled design features of components and backward constraints on the differentiated processing conditions of an enterprise. Therefore, a low-carbon optimization method for tolerance allocation based on surrogate models is proposed. Firstly, the RReliefF algorithm is utilized to analyze the influence of design features and enterprise processing condition factors on the low-carbon performance of tolerance allocation, identifying key influencing factors. Secondly, a convolutional neural network (CNN)-based surrogate model is established to predict the low-carbon performance of tolerance allocation. Specifically, datasets of tolerance, manufacturing costs, and carbon emissions under different design feature constraints are constructed. To improve the training efficiency and accuracy of the prediction model, the heterogeneous data of design features are processed using the one-hot encoding technique. Subsequently, the mapping relationship between tolerance, cost, and carbon emissions is established based on the CNN. Finally, with the aim of minimizing costs and carbon emissions, a low-carbon optimization method for tolerance allocation is established based on the surrogate model and the product size chain. The convolutional neural network-Harris Hawk optimization algorithm (CNN-HHO) is utilized to generate tolerance allocation schemes that minimize both cost and carbon emissions while satisfying dimensional precision. Through a series of multi-peak test functions and practical case studies of the overrunning clutch, the results indicate that the proposed CNN-HHO algorithm demonstrates exceptional accuracy and stability in the validation on the test functions. Furthermore, the optimized overrunning clutch solution achieves approximately 2.61% cost reduction and 2.63% decrease in carbon emissions, providing further support for the effectiveness of the proposed method.

Reconstruction of denuded stratigraphic paleosurfaces of diverse folds based on structural element feature constraints

Reconstructing the stratigraphic paleosurfaces of a fold is essential for deciphering the folding mechanism, simulating landscape evolution processes, and investigating mineral resource distribution. However, standard methods for reconstructing paleosurfaces in tectonic landforms, primarily applied on large-scale sedimentary basins and orogenic belts, heavily rely on extensive geological data and generally yield low-accuracy results. This limits their applicability to small to intermediate-scale geological structural areas. Therefore, this paper introduces a stratigraphic paleosurface reconstruction method tailored for small and intermediate-scale folds, leveraging structural element features to constrain this reconstruction, which is notably helpful when dealing with sparse geological and topographic data. This method involves several steps. Firstly, define the fold units for diverse landforms. Secondly, extract fold structural elements (FSEs) with diverse geological data. Next, fit the paleo-boundary of each stratum within the two-dimensional (2D) cross-section using elemental feature constraints. Finally, the Morphing technique is applied to interpolate multiple paleo-boundaries, which are then utilized in reconstructing the stratigraphic paleosurfaces through the Contour Reconstruction Algorithm (CRA). To validate the method, tests were conducted on three representative folds in China: the eastern Sichuan comb-like fold belt, the Dayueshan Anticline on Mount Lu, and the Wulongshan Dome near the Huangling Dome. Experimental results demonstrate that utilizing structural features as constraints enables automatic, accurate, and reliable stratigraphic paleosurface reconstruction. The reconstructed paleosurfaces facilitate the analysis of geometric characteristics and structural development mechanisms of folds within the study area. Furthermore, they can be readily incorporated into landscape evolution models (i.e., TTLEM) to simulate realistic topographic evolution and tectonic paleogeographic mapping or construct three-dimensional (3D) solid models.

Power Forecasting for Photovoltaic Microgrid Based on MultiScale CNN-LSTM Network Models

Photovoltaic (PV) microgrids comprise a multitude of small PV power stations distributed across a specific geographical area in a decentralized manner. Computational services for forecasting the output power of power stations are crucial for optimizing resource deployment. This paper proposes a deep-learning-based architecture for short-term prediction of PV power. Firstly, in order to make full use of the spatial information between different power stations, a spatio–temporal feature fusion method is proposed. This method is capable of exploiting both the power information of neighboring power stations with strong correlations and meteorological information with the PV feature data of the target power station. By using a multiscale convolutional neural network–long short-term memory (CNN-LSTM) network model, it is capable of generating a PV feature dataset containing spatio–temporal attributes that expand the data source and enhance the feature constraints. It is capable of predicting the output power sequences of power stations in PV microgrids with high model generalization and responsiveness. To validate the effectiveness of the proposed framework, an extensive numerical analysis is also conducted based on a real-world PV dataset.

OMS-SLAM: dynamic scene visual SLAM based on object detection with multiple geometric feature constraints and statistical threshold segmentation

Abstract SLAM technology is crucial to robot navigation. Despite the good performance of traditional SLAM algorithms in static environments, dynamic objects typically exist in realistic operating environments. These objects can lead to misassociated features, which in turn considerably impact the system’s localization accuracy and robustness. To better address this challenge, we have proposed the OMS-SLAM. In OMS-SLAM, we adopted the YOLOv8 target detection network to extract object information from environment and designed a dynamic probability propagation model that is coupled with target detection and multiple geometric constrains to determine the dynamic objects in the environment. For the identified dynamic objects, we have designed a foreground image segmentation algorithm based on depth image histogram statistics to extract the object contours and eliminate the feature points within these contours. We then use the GMS (Grid-based Motion Statistics) matching pair as the filtering strategy to enhance the quality of the feature points and use the enhanced feature points for tracking. This combined method can accurately identify dynamic objects and extract related feature points, significantly reducing its interference and consequently enhancing the system's robustness and localization accuracy. We also built static dense point cloud maps to support advanced tasks of robots. Finally, through testing on the high-speed dataset of TUM RGB-D, it was found that the root mean square error of the Absolute Trajectory Error (ATE) in this study decreased by an average of 97.10%, compared to ORB-SLAM2. Moreover, tests in real-world scenarios also confirmed the effectiveness of the OMS-SLAM algorithm in dynamic environments.

Research on Intelligent Prefabricated Reinforced Concrete Staircase Lifting Point Setting Method Considering Multidimensional Spatial Constraint Characteristics

Prefabricated reinforced concrete staircases (PC staircases) are prefabricated components that are widely used in prefabricated buildings and are used in large quantities. During the production and construction of a PC staircase, the lifting point setting directly affects the construction safety, construction efficiency, and construction quality. In this paper, we analyze the quality problems and safety risks in the design, production, and construction of PC staircases under the constraints of multidimensional spatial characteristics, clarify the key technical difficulties of prefabricated staircase lifting under the multidimensional spatial and temporal constraints, and analyze the factors that should be considered in the setting of lifting points. In this paper, a prefabricated staircase lifting point setting database is established and a thin-plate spline interpolation algorithm is introduced to expand it. Based on the support vector machine algorithm, the process of optimization is carried out for the kernel function scale parameter and penalty factor, and it is concluded that for every increase of two in the number of cross-validation folds, the percentage reduction in minimum RMSE is 9.4%, 17.8%, and 4.2%, respectively, the percentage increase in the optimization time is 39.7%, 61.8%, and 27.3%, respectively, and a PC staircase lifting point setup method based on the small-sample database is proposed. The number of lifting points and lifting point locations of the PC staircase satisfying the multidimensional spatial feature constraints can be obtained by inputting the five design parameters of the PC staircase, namely, the number of treads, the height of the treads, the width of the treads, the width of the staircase, and the weight of the staircase, into the lifting point setup method proposed in this paper. The reliability of the precast reinforced concrete staircase lifting point setting method proposed in this paper when considering the multidimensional spatial constraint characteristics is verified by the precast staircases in deep shafts for assembly construction at the Chongqing metro station.

GLIM: 3D range-inertial localization and mapping with GPU-accelerated scan matching factors

This article presents GLIM, a 3D range-inertial localization and mapping framework with GPU-accelerated scan matching factors. The odometry estimation module of GLIM employs a combination of fixed-lag smoothing and keyframe-based point cloud matching that makes it possible to deal with a few seconds of completely degenerated range data while efficiently reducing trajectory estimation drift. It also incorporates multi-camera visual feature constraints in a tightly coupled way to further improve the stability and accuracy. The global trajectory optimization module directly minimizes the registration errors between submaps over the entire map. This approach enables us to accurately constrain the relative pose between submaps with a small overlap. Although both the odometry estimation and global trajectory optimization algorithms require much more computation than existing methods, we show that they can be run in real-time due to the careful design of the registration error evaluation algorithm and the entire system to fully leverage GPU parallel processing.

Shape-Scale Co-Awareness Network for 3D Brain Tumor Segmentation.

The accurate segmentation of brain tumor is significant in clinical practice. Convolutional Neural Network (CNN)-based methods have made great progress in brain tumor segmentation due to powerful local modeling ability. However, brain tumors are frequently pattern-agnostic, i.e. variable in shape, size and location, which can not be effectively matched by traditional CNN-based methods with local and regular receptive fields. To address the above issues, we propose a shape-scale co-awareness network (S2CA-Net) for brain tumor segmentation, which can efficiently learn shape-aware and scale-aware features simultaneously to enhance pattern-agnostic representations. Primarily, three key components are proposed to accomplish the co-awareness of shape and scale. The Local-Global Scale Mixer (LGSM) decouples the extraction of local and global context by adopting the CNN-Former parallel structure, which contributes to obtaining finer hierarchical features. The Multi-level Context Aggregator (MCA) enriches the scale diversity of input patches by modeling global features across multiple receptive fields. The Multi-Scale Attentive Deformable Convolution (MS-ADC) learns the target deformation based on the multiscale inputs, which motivates the network to enforce feature constraints both in terms of scale and shape for optimal feature matching. Overall, LGSM and MCA focus on enhancing the scale-awareness of the network to cope with the size and location variations, while MS-ADC focuses on capturing deformation information for optimal shape matching. Finally, their effective integration prompts the network to perceive variations in shape and scale simultaneously, which can robustly tackle the variations in patterns of brain tumors. The experimental results on BraTS 2019, BraTS 2020, MSD BTS Task and BraTS2023-MEN show that S2CA-Net has superior overall performance in accuracy and efficiency compared to other state-of-the-art methods. Code: https://github.com/jiangyu945/S2CA-Net.

DualAD: Dual adversarial network for image anomaly detection⋆

AbstractAnomaly Detection, also known as outlier detection, is critical in domains such as network security, intrusion detection, and fraud detection. One popular approach to anomaly detection is using autoencoders, which are trained to reconstruct input by minimising reconstruction error with the neural network. However, these methods usually suffer from the trade‐off between normal reconstruction fidelity and abnormal reconstruction distinguishability, which damages the performance. The authors find that the above trade‐off can be better mitigated by imposing constraints on the latent space of images. To this end, the authors propose a new Dual Adversarial Network (DualAD) that consists of a Feature Constraint (FC) module and a reconstruction module. The method incorporates the FC module during the reconstruction training process to impose constraints on the latent space of images, thereby yielding feature representations more conducive to anomaly detection. Additionally, the authors employ dual adversarial learning to model the distribution of normal data. On the one hand, adversarial learning was implemented during the reconstruction process to obtain higher‐quality reconstruction samples, thereby preventing the effects of blurred image reconstructions on model performance. On the other hand, the authors utilise adversarial training of the FC module and the reconstruction module to achieve superior feature representation, making anomalies more distinguishable at the feature level. During the inference phase, the authors perform anomaly detection simultaneously in the pixel and latent spaces to identify abnormal patterns more comprehensively. Experiments on three data sets CIFAR10, MNIST, and FashionMNIST demonstrate the validity of the authors’ work. Results show that constraints on the latent space and adversarial learning can improve detection performance.

Vision-language constraint graph representation learning for unsupervised vehicle re-identification

Existing vehicle re-identification methods rely on visual features to extract vehicle identity information. However, while individual visual features enable the model to learn limited semantic information, multimodal representations are difficult to extract. A vision-language constraint graph representation learning method guided by textual descriptions is proposed to exploit the cross-modal robustness capacity. Initially, the training set creates the unique conditional prompts for textual feature extraction. These prompts are employed to improve the understanding of visual modalities. We subsequently designed a vision-language constraint graph topology, where each training sample is considered a node in the graph. Under the dual constraints of visual and textual features, the relationship between graph nodes is further explored to construct more reliable positive and negative sample pairs for graph representation learning. Then, neighboring node label smoothing is introduced to mitigate label noise generated by visual feature clustering and achieved by combining pseudo-label assignment results from neighboring node pairs in the graph topology. Extensive experiments have confirmed that the proposed method achieves state-of-the-art performance by combining salient information from visual and textual modalities.

Learning context-aware local feature descriptors for 3D reconstruction

The generation of generalizable and discriminative descriptors plays a crucial role in image matching and 3D reconstruction. While numerous existing solutions are concentrated on encoding specific invariances, such as illumination or viewpoint invariance, they often face challenges in achieving robustness and generalization. These challenges arise from the frequent inadequacy of these solutions to effectively adapt to diverse and demanding environments due to their limited information capacity. In this paper, we introduce a novel approach aimed at maximizing the utilization of hidden feature informativeness to address these challenges. Specifically, we propose the Hierarchical Context-aware Aggregation Network (HCNet), which employs a hierarchical dense features constraint in a coarse-to-refinement description manner. In this approach, a coarse-level descriptor is used to present the overall information, while the refinement descriptor captures the detailed information of the image. Leveraging the strengths of both CNN and Transformer architectures, our hierarchical dense feature constraint encodes both local features and long-range information to efficiently generate dense feature descriptions. To boost descriptor informativeness and enhance matching accuracy, we introduce the Context-aware Attention Aggregation (CAA) model, which adaptively aggregates features from various scales through an efficient coarse-to-refinement manner. Additionally, we design a hierarchical triplet training strategy that considers both variant and invariant properties of hierarchical features, aiming to enhance descriptor informativeness while preserving their strong discriminative qualities. Our experiments, conducted on two popular feature-matching benchmarks, as well as a challenging long-term visual localization benchmark, demonstrate that our method significantly improves matching accuracy and outperforms state-of-the-art descriptors. Moreover, our approach exhibits superior generalization capabilities in various 3D reconstruction scenarios.

Stereo matching from monocular images using feature consistency

AbstractSynthetic images facilitate stereo matching. However, synthetic images may suffer from image distortion, domain bias, and stereo mismatch, which would significantly restrict the widespread use of stereo matching models in the real world. The first goal in this paper is to synthesize real‐looking images for minimizing the domain bias between the synthesized and real images. For this purpose, sharpened disparity maps are produced from a mono real image. Then, stereo image pairs are synthesized using these imperfect disparity maps and the single real image in the proposed pipeline. Although the synthesized images are as realistic as possible, the domain styles of the synthesized images are always very different from the real images. Thus, the second goal is to enhance the domain generalization ability of the stereo matching network. For that, the feature extraction layer is replaced with a teacher–student model. Then, a constraint of binocular contrast features is imposed on the output of the model. When tested on the KITTI, ETH3D, and Middlebury datasets, the accuracy of the method outperforms traditional methods by at least 30%. Experiments demonstrate that the approaches are general and can be conveniently embedded into existing stereo networks.

Learning shared template representation with augmented feature for multi-object pose estimation

Template matching pose estimation methods based on deep learning have made significant advancements via metric learning or reconstruction learning. Existing approaches primarily build distinct template representation libraries (codebooks) from rendered images for each object, which complicate the training process and increase memory cost for multi-object tasks. Additionally, they struggle to effectively handle discrepancies between the distributions of training and test sets, particularly for occluded objects, resulting in suboptimal matching accuracy. In this study, we propose a shared template representation learning method with augmented semantic features to address these issues. Our method learns representations concurrently using metric and reconstruction learning as similarity constraints, and augments response of network to objects through semantic feature constraints for better generalization performance. Furthermore, rotation matrices serve as templates for codebook construction, leading to excellent matching accuracy compared to rendered images. Notably, it contributes to the effective decoupling of object categories and templates, necessitating the maintenance of only a shared codebook in multi-object pose estimation tasks. Extensive experiments on Linemod, Linemod-Occluded and TLESS datasets demonstrate that the proposed method employing shared templates achieves superior matching accuracy. Moreover, proposed method exhibits robustness on a collected aircraft dataset, further validating its efficacy.

A cross-view intelligent person search method based on multi-feature constraints

ABSTRACT Person searches aim to simultaneously locate and identify persons to be queried from different scenes, which is crucial for disaster emergency management and public safety. However, the high variability of environmental features in different video scenes, along with the susceptibility of people searching for occlusions or dense populations, results in existing methods suffering from inefficiency and poor accuracy in searching for cross-view persons. Therefore, we propose a cross-view intelligent person search method based on multifeature constraints. First, we establish the global-local context-aware (GLCA) module, which fully extracts the differential personnel features. Second, we construct the semantic complementarity and feature aggregation (SCFA) module for personnel-scale feature constraints in different contexts. Third, we constrain the method in terms of person spatial, person identity, and detection confidence features to improve person search accuracy. Finally, we construct a case experiment dataset, select two public benchmark datasets, and conduct a detailed experimental analysis based on them. The results show that our method can be applied to personnel search tasks in complex scenarios well, and the search results outperform those of 25 other state-of-the-art algorithms, with mAPs improved by 0.41%−19.71%. This approach effectively enhances the informatization level of disaster emergency rescue and public safety management.

Structural seismic response reconstruction method based on multidomain feature-guided generative adversarial neural networks

Structural seismic response reconstruction is important to assess the safety of structures. This study presents a novel multidomain feature-guided generative adversarial neural network model (MWGAN-TF) for reconstructing the seismic responses of structures, which takes into account the joint non-stationarity of the seismic response in the time-frequency statistical domain. It innovatively incorporates time, frequency, and statistical-domain feature constraints into the multiscale generative adversarial neural network, which guides the model to learn the multidomain feature information of the seismic response at different time scales. A statistical indicator (CNCSI) was proposed to evaluate the performance of the model in capturing nonstationary characteristics. The effectiveness of the MWGAN-TF was verified using response data from numerical models of a three-story moment-resisting frame and reinforced concrete frame structures, as well as the field measurement data of an actual building. Thereafter, the effects of different domain feature-guided models on the reconstruction response accuracy are discussed. The results show that embedding multidomain feature constraints can provide a more reliable response reconstruction by improving the ability of the model to capture nonstationary characteristics. Thus, the deep learning paradigm based on multidomain feature guidance outperforms the classical neural network guided only by time-domain features.

OctOcc: High-Resolution 3D Occupancy Prediction with Octree

3D semantic occupancy has garnered considerable attention due to its abundant structural information encompassing the entire scene in autonomous driving. However, existing 3D occupancy prediction methods contend with the constraint of low-resolution 3D voxel features arising from the limitation of computational memory. To address this limitation and achieve a more fine-grained representation of 3D scenes, we propose OctOcc, a novel octree-based approach for 3D semantic occupancy prediction. OctOcc is conceptually rooted in the observation that the vast majority of 3D space is left unoccupied. Capitalizing on this insight, we endeavor to cultivate memory-efficient high-resolution 3D occupancy predictions by mitigating superfluous cross-attentions. Specifically, we devise a hierarchical octree structure that selectively generates finer-grained cross-attentions solely in potentially occupied regions. Extending our inquiry beyond 3D space, we identify analogous redundancies within another side of cross attentions, 2D images. Consequently, a 2D image feature filtering network is conceived to expunge extraneous regions. Experimental results demonstrate that the proposed OctOcc significantly outperforms existing methods on nuScenes and SemanticKITTI datasets with limited memory consumption.

Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection

Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In addition, some methods lack constraints between parts, which need manual selections of edited results to ensure quality. Therefore, we propose a four-stage process for point cloud part editing: Segmentation, Generation, Assembly, and Selection. Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint. By independently fitting part-level feature distributions, we realize the feature disentanglement. By explicitly modeling the transformation from object-level distribution to part-level distributions, we realize the feature constraint. Considerable experiments on different datasets demonstrate the efficiency and effectiveness of SGAS on point cloud part editing. In addition, SGAS can be pruned to realize unsupervised part-aware point cloud generation and achieves state-of-the-art results.

Geometric information constraint 3D object detection from LiDAR point cloud for autonomous vehicles under adverse weather

3D object detection, as the core of the autonomous vehicle perception module, is essential for efficient transportation and comfortable experiences. However, the challenge of 3D object detection under adverse weather conditions hinders the advancement of autonomous vehicles to higher levels. Hence, achieving accurate 3D object detection under adverse weather conditions is increasingly crucial as it forms the foundation for trajectory planning and driving strategy making in autonomous vehicles, thereby revolutionizing transportation modes for both goods and passengers. Advances in Light Detection and Ranging (LiDAR) technology have facilitated the development of 3D object detection in the past few years. Adverse weather, which inevitably occurs in real-world driving scenarios, could degrade measurement accuracy and point density of LiDAR and lead to particle interference. Detecting accurate 3D bounding boxes from sparse, incomplete point clouds with particle interference is difficult. Therefore, this research presents a novel geometric information constraint network for 3D object detection tasks from LiDAR point clouds under adverse weather (GIC-Net). In this study, we focus on how to incorporate geometric location information and line geometric feature information into the network against adverse weather. Further, we propose a geometric location constrained backbone module (GLC) to reduce rain and snow particle interference and ensure sufficient receptive fields. Then, we design a line geometric feature constraint module (LGFC) to add line constraints of 3D bounding boxes into the training process. Finally, a line loss function is designed, and features from the GLC and LGFC modules are fed into the multi-task detection head for accurate 3D bounding box prediction. Experiments on the Canadian Adverse Driving Conditions (CADC) autonomous vehicle dataset demonstrate the superiority of our method over six other state-of-the-art methods under adverse weather, which is at least 13.32 %, 4.67 %, and 10.44 % mAP higher than the other compared methods in the car, truck, and pedestrian classes respectively. Also, we further verify the better generalization ability of our network compared to other methods.

A Refined Wind Power Forecasting Method with High Temporal Resolution Based on Light Convolutional Neural Network Architecture

With a large proportion of wind farms connected to the power grid, it brings more pressure on the stable operation of power systems in shorter time scales. Efficient and accurate scheduling, operation control and decision making require high time resolution power forecasting algorithms with higher accuracy and real-time performance. In this paper, we innovatively propose a high temporal resolution wind power forecasting method based on a light convolutional architecture—DC_LCNN. The method starts from the source data and novelly designs the dual-channel data input mode to provide different combinations of feature data for the model, thus improving the upper limit of the learning ability of the whole model. The dual-channel convolutional neural network (CNN) structure extracts different spatial and temporal constraints of the input features. The light global maximum pooling method replaces the flat operation combined with the fully connected (FC) forecasting method in the traditional CNN, extracts the most significant features of the global method, and directly performs data downscaling at the same time, which significantly improves the forecasting accuracy and efficiency of the model. In this paper, the experiments are carried out on the 1 s resolution data of the actual wind field, and the single-step forecasting task with 1 s ahead of time and the multi-step forecasting task with 1~10 s ahead of time are executed, respectively. Comparing the experimental results with the classical deep learning models in the current field, the proposed model shows absolute accuracy advantages on both forecasting tasks. This also shows that the light architecture design based on simple deep learning models is also a good solution in performing high time resolution wind power forecasting tasks.