80 results about "Traffic sign recognition" patented technology

The invention discloses an improved YOLOv11-based traffic sign identification and detection method, which comprises the following steps: based on a backbone network of YOLOv11, providing an IPC3k2 layer, replacing standard convolution by Ghboost to realize lightweight feature extraction, embedding a Coard coordinate attention mechanism in Bottleneck to strengthen space positioning capability, and combining a double-branch Ghboost feature fusion strategy; a SomSPPF module is provided for the trunk part, and a multi-scale deformable pyramid pooling module, a two-dimensional attention mechanism module and a SamReBlock re-parameterization convolution module are fused; in a neck network, an MSCATR attention module is added, dynamic channel fusion is adopted to realize dynamic fusion of channel statistical guidance, cross-space fusion is utilized to establish a space cooperation mechanism, an adaptive feature fusion module is introduced, and finally residual multi-level feature optimization is realized through learnable weight parameters. Compared with the prior art, the method has the advantages that the accuracy of traffic sign detection of the YOLOv11 model can be effectively improved, and the advantages of real-time performance and robustness of the model are considered.

This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, the methods addresses traffic sign recognition as a language model-based image reasoning task by utilizing a multi-modal transformer architecture that combines the strength of vision and language machine learning (ML) models. The transformer architecture recognizes traffic signs based on visual features and associated taxonomy of the traffic signs. In a second aspect, the methods leverage context surrounding an autonomous vehicle through a graph-based modeling framework that fuses outputs from multiple perception modules to construct a semantic scene graph representation of an intersection, which consolidates processing diverse data types for traffic light relevancy detection. Other aspects and features are also claimed and described.

The invention discloses a traffic sign recognition and lane line detection method and system for extreme weather, and relates to the technical field of computer vision and artificial intelligence. According to the method, an efficient image restoration algorithm is designed, the influence of haze, rain and snow and other weather noise on the image quality is eliminated, and key detail information of traffic signs and lane lines is reserved; secondly, a YOLOv8 target detection network is improved, the problems of missing detection of small targets and false detection of complex backgrounds are solved, and the detection accuracy of the multi-scale traffic signs is improved; furthermore, a lightweight lane line detection algorithm is designed based on an improved line anchor mechanism, and the detection precision and real-time performance of the lane line in a complex scene are improved; and finally, an image restoration module, a traffic sign recognition module and a lane line detection module are integrated, multi-modal support of images, videos and real-time camera data is realized, an engineering solution adaptive to extreme weather is formed, and practical application of an intelligent traffic system in a complex environment is promoted.

The invention relates to an active traffic sign identification method and device based on fusion of multiple cameras. Comprising the steps that in the vehicle driving process, a vehicle-mounted panorama camera collects and recognizes a plurality of marks in a panorama image, tracking is conducted, the confidence degree of the marks is judged, the marks with the confidence degree lower than a preset threshold value are input into a sorting module to be sorted according to importance indexes, and the marks are sequentially set as current target marks according to the sorting of the importance indexes; and adjusting the target angle of the long-focus camera according to the changed relative position of the current target sign in the vehicle driving process, collecting a high-definition image for high-definition identification, and performing data fusion on a high-definition identification result and a preliminary identification result to generate a traffic sign identification result. According to the embodiment of the invention, the method achieves the efficient combination of a panoramic camera and a long-focus camera in a traffic sign recognition process, greatly improves the recognition performance, and effectively expands the detection and recognition range of traffic signs.

The invention relates to an adversarial sample generation method and equipment for a road traffic sign recognition model. The method comprises the following steps: constructing a traffic sign recognition model; training the traffic sign recognition model through a deep learning technology to obtain a traffic sign image preliminary recognition effect; adversarial disturbance is added on the basis of the preliminary recognition effect on the traffic sign image, and an adversarial sample for the model is generated; a real scene image influenced by illumination, weather and stain interference is generated through physical environment simulation, and attack testing is carried out in combination with an adversarial sample; and evaluating the generated confrontation sample according to a test result, judging whether the confrontation sample is completed or not, and if not, repeating the attack test until the evaluation reaches the standard to complete the generation of the confrontation sample. Compared with a traditional method, attack generalization is ensured through confrontation of multiple discriminators under attack scene simulation, and rationality of the image is ensured by adding multiple interference factors.

The invention relates to the technical field of computer vision and deep learning, in particular to a traffic sign recognition method based on an MCA attention mechanism, and the method comprises the steps: firstly obtaining an input image, extracting a multi-level feature map through a backbone network, and then applying the MCA attention mechanism which comprises an extrusion transformation module, an excitation transformation module and an integration module, the method comprises the steps that firstly, an enhanced feature map is generated, then, multi-scale feature fusion is conducted through a four-head ASFF detection head, a fusion feature map is generated, a normalized Wasserstein distance loss function is calculated according to the fusion feature map, detection and recognition of traffic signs are achieved, the category and position information of the traffic signs is output, and through an MCA attention mechanism, the traffic signs are recognized. The perception capability of the network for key features of traffic signs is enhanced, the richness of feature expression is improved, the model can better pay attention to multi-scale and small-target traffic signs, and the feature discrimination capability is improved compared with a traditional attention mechanism.

The invention discloses a lightweight traffic sign recognition method fusing time sequence characteristics in a shielding scene, and relates to the field of computer vision and intelligent traffic, in particular to a traffic sign recognition technology. Respectively constructing a single-frame data set with slight occlusion and a time sequence data set with severe occlusion; for a street scene image containing a complex background, training a lightweight target detector YOLOv8-N based on an existing bounding box label in a data set; secondly, a depth separable convolution structure with MobileNetV2 as a trunk network is adopted, and a high-dimensional feature map is extracted from the candidate mark image; then, a space attention mechanism is introduced, weighted correction is carried out on input features, an unshielded region is strengthened, and a shielded and noise region is suppressed; and finally, extracting a feature sequence of a historical frame of a heavily shielded sample, and inputting the feature sequence into an extended long-short-term memory network xLSTM for time sequence fusion.

The invention relates to the technical field of image recognition, and discloses a lightweight traffic sign recognition method based on loss function optimization and module improvement, which comprises the steps of collecting traffic sign image data for preprocessing, segmenting an image background, extracting image features and performing dimension reduction processing, and recognizing and classifying the image features. And traffic sign identification processing in different images is realized. According to the lightweight traffic sign recognition method and system based on loss function optimization and module improvement, in a YOLOv8s backbone network, a lightweight GhostConv module is used for replacing a traditional convolution module, the model compression performance is achieved, the detection speed and accuracy are kept, a DWConv module is added into a head network, model parameters are reduced, the feature fusion efficiency is improved, and the method and the system have the advantages that the model compression performance is improved, and the detection speed and accuracy are improved. An attention mechanism DAttention is introduced to enhance the extraction effect of related features, irrelevant features are inhibited to improve the detection precision of the algorithm, bounding box regression is more accurate by optimizing a loss function and combining a Shape-IoU method, and the model detection performance is effectively improved.

The application discloses a night traffic sign recognition method and system based on deep learning and a storage medium. The application relates to the technical field of intelligent traffic, and is built based on an existing deep neural network to form a night traffic sign recognition model, so that the night traffic sign can be accurately and quickly recognized in a night environment. The night traffic sign recognition method based on deep learning proposed by the application enhances the adaptability of the model to the night environment through image preprocessing and improved backbone network, effectively alleviates the problems of false detection and missed detection of the model to the traffic sign in the night environment, improves the recognition accuracy of the model, and ensures the recognition speed.

The application discloses a traffic sign recognition method and system for active safety of commercial vehicles, and specific steps of the recognition method are as follows: S1, capturing road panoramic image information through a vehicle-mounted camera device, and performing pretreatment operation on the road panoramic image information, and setting a threshold value through color transformation space to extract an image of a region of interest; S2, matching the image of the region of interest with a traffic sign template library picture, and positioning a sign image in the road panoramic image according to a matching result; S3, designing and building a neural network model, training the neural network model on a sampling traffic sign data set, and obtaining an optimal traffic sign recognition model; S4, merging a multi-branch structure in the optimal traffic sign recognition model, and obtaining a remodeling model; S5, performing classification recognition on the sign image in step S2, inputting the sign image into the remodeling model in step S4 after normalizing the sign image, and judging a traffic sign type according to an output result.

The invention relates to the technical field of computer vision and intelligent traffic, and discloses a traffic sign intelligent detection method and system based on deep learning, and the method comprises the steps: obtaining a traffic sign image of a road, and generating a preprocessed traffic signal sign image through marking and preprocessing; constructing an improved traffic sign recognition and detection model; inputting the preprocessed traffic signal sign image into an improved traffic sign recognition and detection model for training, and optimizing by using an improved loss function to obtain a trained improved traffic sign recognition and detection model; acquiring a to-be-recognized traffic sign image of a road in real time, and after data processing, inputting the to-be-recognized traffic sign image into the trained improved traffic sign recognition and detection model for traffic sign detection to obtain a traffic sign detection result; according to the invention, the real-time performance is ensured, and the detection precision of various traffic signs is obviously improved.

The invention relates to a method for controlling a driver assistance system in a road vehicle (22) having an electronically controllable drive motor (24) and an electronically controllable service brake system having wheel brake cylinders (30, 32, 34, 36) which can be actuated with pressure medium, and having a camera-based vehicle recognition, pedestrian recognition and traffic sign recognition, as well as a speed regulation function and an emergency brake function, wherein, when the road vehicle (22) approaches an identified bus stop or tram stop (2), the controller (26) of the driver assistance system, in addition to generating and outputting a warning signal to the driver of the road vehicle (22), also carries out at least one further measure to avoid a collision with a pedestrian (14.1, 14.2, 14.3). As an additional measure, according to the invention, the wheel brake cylinders (30, 32, 34, 36) of the service brake system of the road vehicle (22) are pre-filled with a predetermined fluid pressure before reaching the bus stop or tram stop (2) in order to prepare for a possible emergency brake. The invention also relates to a device (40) for carrying out the method.

This invention provides a traffic sign recognition method and related apparatus. The method includes: acquiring real-time image data and environmental data collected during vehicle movement; concatenating the preprocessed environmental data into an environmental vector, and generating a modulation vector based on the environmental vector; applying channel attention modulation to a feature map using the modulation vector to obtain a modulated multi-scale image feature map; performing feature recalibration processing on the multi-scale image feature map to obtain a recalibrated feature map; performing traffic sign detection based on the recalibrated feature map and outputting an interpretable detection result for the traffic sign; and performing online incremental learning on the target detection model based on the interpretable detection result according to preset triggering conditions, and collaborating with a cloud server through federated aggregation. Based on this, this invention can intelligently recognize traffic signs, obtain interpretable detection results, and support online incremental learning.

The present invention provides a method and device for improving traffic sign recognition of YOLOv3. The method includes collecting a number of traffic sign pictures to obtain a data set; preprocessing the data set based on a preset data augmentation method; dividing the preprocessed data set into a training set and a test set; introducing channel attention to enhance the depth network in the YOLOv3 network model to obtain an improved YOLOv3 network model; inputting the training set into the improved YOLOv3 network model for training and using the test set for verification to obtain a trained YOLOv3 network model; and using the trained YOLOv3 network model to recognize traffic signs. By performing data augmentation processing on the pictures, overfitting can be effectively prevented while the generalization ability of the model is increased. By introducing channel attention to enhance the depth network in the network model, the accuracy of traffic sign recognition can be improved and the efficiency of traffic sign recognition can be enhanced.

This invention proposes a traffic sign light-sensing algorithm, device, and system based on an improved HSV (High-Speed ​​Vector Characteristic). The light-sensing algorithm includes: using adaptive HSV threshold adjustment combining global brightness statistics and local block segmentation to generate a dynamic HSV threshold suitable for the current scene; and using this dynamic threshold to perform color segmentation on the image to obtain the target color region. Compared to the inherent HSV threshold, or solely global brightness statistics, or solely local block adaptive threshold correction, this overcomes the interference of different reflectivities and absorbances of objects in the environment, which cause interference in color recognition of different regions of the image under complex lighting conditions such as strong light, weak light, backlight, and local shadows. This significantly improves the robustness and accuracy of traffic sign recognition in dynamic, unstructured scenes.

The invention provides a traffic sign target recognition method based on deep meta-learning, a medium, equipment and a product, and relates to the technical field of meta-learning, and the method comprises the steps: obtaining a traffic sign image, and dividing the image into a training task set and a test task set; the method comprises the following steps: constructing a deep meta learning model by taking CNN as a meta network of meta learning and a structure of each task network, optimizing an MAML meta learning algorithm by using a ZeroTrick strategy on the basis of Meta-SGD, and setting a linear layer weight parameter as 0 after the algorithm starts and each sampling task cycle ends; and training the deep meta-learning model by using the training task set, testing the trained deep meta-learning model by using the test task set, and using the tested model for traffic sign target identification. According to the invention, the generalization ability and accuracy of the traffic sign recognition model under the condition of few samples are improved.

Embodiments of the present application provide a traffic sign recognition method, an electronic device, a storage medium and a program product. The method comprises: obtaining attribute information of multiple traffic signs on the same road from map update data; determining corner point road coordinates and sign face projection areas of the multiple traffic signs in a road coordinate system according to the attribute information; performing clustering processing on the multiple traffic signs according to the corner point road coordinates and the sign face projection areas, to obtain multiple target clustering clusters; for each target clustering cluster, determining a target type of a target traffic sign based on the corner point road coordinates and the sign face projection areas of the target traffic sign included in the target clustering cluster; and the target type is a side-by-side combined type or a composite combined type. The method is used to improve the recognition accuracy of traffic signs.

The invention provides a traffic sign recognition test system and method, a medium and equipment, a supporting base, a telescopic rod, a rotating support, a signboard frame base and a double-sided signboard are arranged, the telescopic rod is arranged on the supporting base, the rotating support is arranged at the end, away from the supporting base, of the telescopic rod, and the signboard frame base is arranged on the rotating support; the rotating support is used for driving the signboard frame base to horizontally rotate relative to the supporting base, the double-face signboard is arranged on the signboard frame base, and different traffic signs are arranged on the two faces of the double-face signboard respectively. By arranging the entity signboard, the electromagnetic interference is reduced, so that the test accuracy is improved, and by arranging the rotatable double-sided signboard, the test efficiency and convenience can be improved.

A traffic sign recognition device includes a storage device configured to store a camera image from a movable body and pieces of three-dimensional point group data, and a processor. The processor is configured to: estimate a relative position of the traffic sign candidate to the movable body; specify a set of three-dimensional point group data; and specify an image region of an object corresponding to a set region indicative of a region where the set is specified, the object including the traffic sign candidate. The processor is configured to calculate a percentage of a predetermined color component constituting a guide sign among color components constituting an image of the object. In a case where the percentage of the predetermined color component is equal to or more than a threshold, the processor recognizes the object including the traffic sign candidate to be the guide sign.

The invention relates to a method for operating a driver assistance device for a motor vehicle, which has a position determination device for determining a current position of the motor vehicle, a traffic sign recognition device for recognizing a traffic sign, a data memory for storing at least one route profile and a display device for displaying a recommended course of action.The following steps are provided: recognition of a traffic sign by the traffic sign recognition device and recording a traffic sign position based on the current position of the motor vehicle during at least a first journey of the motor vehicle, and storage of the traffic sign position and traffic sign information describing the traffic sign in the data memory in the form of at least one traffic sign data record; creation of a recommended course of action based on the at least one stored route profile and the traffic sign information stored in the at least one data record during at least one second journey of the motor vehicle following the first journey, and carrying out longitudinal and / or transverse guidance of the motor vehicle based on the recommended course of action and / or displaying the recommended course of action to the driver of the motor vehicle using the display device.The invention further relates to a corresponding driver assistance device for a motor vehicle.

The invention relates to a vehicle (2) with a system (1) for camera-based traffic sign recognition, in which, during driving operation, an actual image of the traffic sign (B) is displayed by means of a camera (5). ist ) is detectable, wherein the system (1) is based on the detected traffic sign actual image (B ist ) a speed recommendation (v E ) for the driver. According to the invention, the system (1) has an analysis module (13) which, in the event of a driver-initiated speed correction measure that leads to a deviation from the speed recommendation (v E ) differing actual speed (v ist ) performs an error analysis to check whether or not there is a fault in the traffic sign recognition system (1).

The embodiment of the invention provides a traffic sign recognition model training method and device, electronic equipment and a computer readable medium. The training method of the traffic sign recognition model comprises the following steps: acquiring image data of a traffic sign based on traffic sign images acquired by a vehicle-mounted camera under different weather conditions; transform mapping is carried out on the image data to obtain enhanced data, and the transform mapping mode comprises at least one of rotation, miscutting, translation and zooming; and training the model based on the enhanced data.

This application provides a method, apparatus, control device, storage medium, and product for traffic sign recognition, belonging to the field of artificial intelligence technology. The method first enhances the acquired road image. This enhances the contrast, saturation, and brightness of the area containing the traffic signs in the first road image, creating a strong contrast between the traffic signs and the image background. This facilitates the feature extraction network in capturing effective semantic information, thereby simplifying the recognition of traffic signs in the road image. Then, based on the enhanced road image, a sign recognition model is used for recognition. Since the traffic sign recognition model employs a lightweight convolutional neural network (CNN), which has fewer parameters and lower computational complexity, its operating efficiency and inference speed can be improved, enabling real-time traffic sign recognition and thus enhancing the safety of autonomous driving.

The invention provides a traffic sign recognition method and device and a storage medium, and belongs to the technical field of sign recognition, and the method comprises the steps: importing a plurality of original traffic sign pictures, carrying out the preprocessing of all original traffic sign pictures, and collecting the preprocessing results to obtain a preprocessed traffic sign picture set; dividing the preprocessed traffic sign picture set into a traffic sign training set and a traffic sign test set according to a preset proportion; and constructing a training model, and training the training model through the traffic sign training set to obtain a to-be-processed model. The problem of traffic sign recognition in severe weather can be solved, the reliability and safety of an automobile auxiliary driving system in a complex environment are improved, the life safety of drivers and passengers is guaranteed, high-quality development of the automobile industry and the intelligent network connection technology is promoted, and key technical support is provided for intelligent traffic system construction.

The invention discloses a traffic sign recognition method based on a random Fourier feature visual state space model, and belongs to the technical field of computer vision, deep learning and intelligent traffic systems. The objective of the invention is to solve the problems of spectrum deviation, poor multi-scale adaptability and lack of uncertainty perception of the existing visual state space model. A hierarchical probabilistic network architecture (MS-RFF-VSSM) is constructed, a traffic sign image is mapped to a high-dimensional random feature space by using a kernel approximation technology through a hierarchical variational random Fourier feature embedding module, and meanwhile, the uncertainty of prediction is explicitly quantized based on a Bayesian framework; secondly, designing a multi-scale attention fusion module and a multi-scale receptive field visual state space backbone network, and considering global context modeling and adaptive extraction of local multi-scale features while keeping linear calculation complexity; and finally, carrying out dynamic weighting on the sampling features through a class attention prediction module to output a classification result. According to the method, the recognition precision and robustness of the model in a complex dynamic environment can be remarkably improved under the condition of relatively low parameter quantity, and the balance between the precision and the calculation efficiency is realized.

The invention relates to a method for improving the detection of road users who are outside the detection range of a sensor device of a vehicle for controlling an ADAS / ADS system, comprising the following steps: - detecting sensor data (220) of a traffic scene and surroundings of a vehicle (10) with an ADAS / ADS system (750) by sensors of a sensor device (220) of the vehicle (10); - Preprocessing the sensor data (220) and / or the fused sensor data (250) by an input layer (430) of an AI model (410) of the evaluation module (400), in particular for noise reduction and generating preprocessed sensor data (435); - Processing the preprocessed sensor data (435) by a first task layer (440) with an algorithm for detecting and tracking other vehicles, a second task layer (450) with an algorithm for traffic sign recognition, a third task layer (460) with an algorithm for predicting the trajectories of other vehicles, and a fourth task layer (470) with an algorithm for detecting road users such as pedestrians or animals to create processed input data (510, 520, 530, 540) for a decision model (500) - Merging processed input data (510, 520, 530, 540) into a fused context.

A safety warning device for deactivated driver assistance systems, hereinafter referred to as SWEFF, is characterized in that, when driver assistance systems (e.g., ABS (Anti-lock Braking System), TC (Traction Control), Slide Control, Wheelie Control, Engine Brake Control, ESP (Electronic Stability Program), Traffic Sign Recognition, Emergency Brake Assist, Lane Keeping Assist, etc.) are deactivated, the entire display or parts of the display flash (at least once) and / or an acoustic signal sounds at least once and / or a voice output is given at least once (e.g., via loudspeaker and / or a communication system in and / or on the helmet). The flashing and / or the acoustic signal and / or the voice output can be repeated after a certain period of time.This repetition can be prevented by the driver through various actions (e.g., pressing a control button and / or touching a touchscreen (e.g., display) and / or by voice input (e.g., via a microphone) and / or in a menu (software)). In vehicles with analog instruments, the instrument lighting or parts of the instrument lighting and / or at least one indicator light may flash. There may then be a separate indicator light for each driver assistance system.

The invention relates to the technical field of image recognition, and discloses a local occlusion traffic sign recognition method based on an attention enhancement CNN, and the method comprises the following steps: carrying out the dynamic occlusion data enhancement processing of an input traffic sign image, and obtaining an enhanced traffic sign image; inputting the enhanced traffic sign image into a lightweight convolutional neural network; the lightweight convolutional neural network performs primary feature extraction, intermediate feature fusion and advanced feature abstraction in sequence through a pyramid type multi-stage feature decoupling module; in the advanced feature abstraction process, hole depth separable convolution is adopted to process the feature map; and outputting the prediction probability of each type of traffic sign through the last full connection layer to obtain an identification result. According to the method, through dynamic occlusion data enhancement processing, block occlusion, Gaussian noise occlusion, geometric transformation and luminosity transformation are applied to the input image in the training stage, so that the stable recognition capability of the partially occluded image is kept in the reasoning stage.

The application provides a road traffic sign recognition method based on image semantic understanding, which comprises the following steps: image acquisition based on an image acquisition device, pretreatment of the collected image, construction of a road traffic sign data set, construction of a road traffic sign detection model based on a Blip network, training of the model based on the road traffic sign data set, obtaining of the trained road traffic sign detection model, and effect test of the trained road traffic sign detection model based on the road traffic sign data set. The application can recognize road traffic signs and generate sentence descriptions of the signs from the aspects of color, shape and composition, recognize lane types from a macro perspective, avoid dependence on annotated signs, realize efficient and accurate traffic sign recognition in a complex environment, and have high practical value.

The present specification relates to a kind of active traffic sign recognition method and device based on the fusion of multiple cameras. Including: in the vehicle driving, vehicle-mounted panoramic camera collects and identifies multiple signs in panoramic image, carries out tracking, and judges the confidence of multiple signs, the sign with confidence lower than preset threshold is input sorting module according to importance index and is sorted, and according to the importance index, it is sequentially set as current target sign;According to the relative position of current target sign in the change of vehicle driving, the target angle of long-focus camera is adjusted, and high-definition image is collected to carry out high-definition identification, the result of high-definition identification is fused with the result of preliminary identification, and traffic sign recognition result is generated. The present specification embodiment realizes the efficient combination of panoramic camera and long-focus camera in the process of traffic sign recognition, greatly improves the recognition performance, and then effectively expands the range of traffic sign detection and recognition.