117 results about "Traffic sign recognition" patented technology

The invention discloses a small target traffic sign recognition method based on improved YOLOv8, and the method comprises the steps: constructing a data set, selecting sample pictures from the data set, carrying out the labeling and data enhancement, and dividing the data set into a training set and a test set; the YOLOv8 model is improved, and a multi-scale attention mechanism EMA is embedded in a backbone network of the YOLOv8 model; an up-sampling operator in a neck network of the YOLOv8 model is replaced by a DySample up-sampling operator; replacing an original loss function CIoU of the YOLOv8 model with a WIoUv3 loss function; and inputting the training set into the improved YOLOv8 model for training, after training is completed, detecting the detection performance of the improved YOLOv8 model by using the test set to obtain an identification result, and evaluating the performance of the improved YOLOv8 model by using various indexes. According to the small target traffic sign identification method based on the improved YOLOv8, the identification precision and the identification speed of the small target traffic sign can be effectively improved.

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 provides an anti-dazzling traffic sign generation system, device and method, and the method enables the image data used for detection to be accurately recognized in a weak light environment through the preprocessing of the environment image data during the operation of a vehicle. Traffic sign recognition and screening and anti-dazzling target recognition and screening are carried out on the image data, and finally a traffic sign icon with a shielding frame is generated; the traffic sign icon with the shielding frame can effectively prevent light rays of a projection light machine from directly irradiating the retina of pedestrians or other drivers, the dazzling feeling is relieved, and more convenient and clearer driving instructions, driving safety of the drivers and visual protection of other road users are provided by optimizing the definition of the projection sign.

The invention relates to the technical field of target detection, in particular to a traffic sign defogging detection method based on improved MSR-YOLO, and various traffic sign pictures in a foggy environment are collected by using vehicle-mounted monitoring. A multi-scale adaptive network module MS is used for carrying out defogging preprocessing, the multi-scale adaptive network module MS improves image quality and detail representation through three different-scale convolution kernels, and then defogging processing is carried out through a dark channel prior defogging filter, a Gamma filter and a sharpening filter in sequence. Based on YOLOv11 network improvement, a C3K2-RFAConv module is introduced into a Backbone part and a Neck part to replace a C3K2 module, RFAConv of the Backbone part replaces a traditional convolution module, a traffic sign detection network model is obtained, and a data set is used for training the traffic sign detection network model. And carrying out target detection on the defogged image by using the trained traffic sign detection network model. Compared with the prior art, the influence of the foggy environment on traffic sign recognition can be effectively reduced, so that the foggy traffic sign detection accuracy is improved.

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 discloses a traffic sign identification method and apparatus, and an electronic device. The method comprises the following steps: acquiring a traffic sign image in a traffic driving scene; performing super-resolution reconstruction processing on the traffic sign image to obtain a high-resolution image of the traffic sign image; a traffic sign recognition model is adopted to analyze the high-resolution image to obtain a recognition result corresponding to the traffic sign image, the traffic sign recognition model comprises a backbone network, a neck network and a head network, the backbone network is used for carrying out multi-level feature extraction on the high-resolution image through a target converter to obtain a multi-level feature map, and the head network is used for carrying out multi-level feature extraction on the high-resolution image; the neck network is used for fusing the multi-level feature maps through the feature pyramid network and the path aggregation network, and the head network is used for identifying the fused feature maps through a target loss function to obtain an identification result. According to the invention, the technical problems of high omission ratio, poor detection precision and slow identification speed caused by unclear traffic sign images are solved.

The invention discloses a no-reference vehicle image quality evaluation method and equipment based on saliency perception. A large-scale no-label vehicle image data set is utilized, and image distortion recognition models for distinguishing different types and grades are trained in a self-supervision mode; training a model for detecting the salient region in the image by using the salient region segmentation data set; a pre-trained distortion quality perception module and a pre-trained saliency region segmentation module are used to acquire a saliency feature map and a distortion feature map in an input image, and then a weight matrix is constructed and applied to realize weighted fusion between the saliency feature map and the distortion feature map so as to generate a new comprehensive feature map; and sending the generated comprehensive feature map into a multi-layer perceptron, and outputting a score reflecting the overall quality of the image after processing. The method not only improves the accuracy of image quality evaluation, but also enhances the practical application value and generalization ability of the model. The method is of great significance in key tasks such as pedestrian detection and traffic sign recognition.

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.

A real-time traffic sign recognition system consisting of: a neural network module configured to process input images containing traffic signs; a lightweight, shallow information enhancement module configured to split input feature maps into multiple parts, apply a depth-wise convolution to each part, apply a pointwise convolution to combine fitted values, and concatenate features from each processed part; a customizable channel attention mechanism configured to perform global maximum pooling and global average pooling for input features, combine pooled results using customizable parameters, encode and decode the compressed features through fully connected layers, and generate channel attention coefficients; a cross-stage sub-module configured to implement window-based multi-head self-attention for local feature processing, capture context information around traffic signs, and combine features of convolutional neural networks with transformer features; and an adaptive feature fusion module configured to generate learnable weights for feature fusion, combine features from different network layers, and output detected traffic signs with location information.

The invention provides a traffic sign recognition model training method, system and device, a medium and a traffic sign recognition method.The first training stage of the traffic sign recognition model training method comprises the steps that a clear image is collected, and noise adding and noise reduction processing is conducted on the clear image; the second training stage comprises the following steps: acquiring initial features of various types of traffic signs, constructing an initial feature memory bank, calculating feature centers of the various types of traffic signs by using training sample images, and calculating restoration loss between the images after noise reduction and original clear images so as to adjust noise reduction parameters of the model. Updating the initial feature memory library to obtain template feature representation, and finally extracting sampling features of a target sample image and calculating comparison loss between the sampling features and template features of the same category to adjust feature extraction parameters of the model; according to the method, the noise reduction capability and the feature extraction capability of the traffic sign recognition model are respectively improved through the recovery loss and the comparison loss, so that the recognition accuracy and robustness of the model are enhanced.

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 provides a traffic sign detection method and device based on clustering analysis, and belongs to the technical field of traffic sign detection. The method comprises the following steps: preprocessing a multi-disturbance traffic sign data set, and determining a first centroid of the data set; calculating a non-connectable data set based on the data set, and sorting the first centroids to obtain a second centroid; and updating the data set by using the non-connectable data set to obtain a first data set, pulling data points of the first data set to a second centroid, performing updating, aggregation and separation processing on the data after data translation based on the first data set to obtain a second data set, and performing data clustering to obtain a data clustering result. The method comprises the following steps: acquiring an optimal unsupervised contour coefficient, marking unmarked original data on the basis of a clustering result of the optimal unsupervised contour coefficient, obtaining a marked multi-disturbance traffic sign data set, carrying out model training, identifying a to-be-identified traffic sign by adopting a trained traffic sign detection model, and determining the type of the traffic sign. According to the invention, data interference in a traffic sign identification process can be reduced.

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 invention provides a traffic sign image recognition method based on personalized federal learning, is applied to the field of intelligent Internet of Things, and provides an improvement scheme for the influence of common non-independent identically distributed data on each vehicle client while realizing basic traffic sign image recognition. A super network mechanism is introduced into a server side, a unique super network is formed for each vehicle client side in the process, and hierarchical learning of a model and a similar data model is facilitated from all the vehicle client sides. And meanwhile, when the server model is loaded on each vehicle client, judging a layer granularity coefficient when the client aggregates the global model according to a difference value between the local model and the global model, and updating a corresponding aggregation weight according to the layer granularity coefficient. The system can be used in the fields of intelligent Internet of Things traffic sign recognition, automatic navigation traffic sign recognition systems and the like.

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).