67 results about "Frame difference" patented technology

Systems, apparatus, and methods for post-processing video e.g. frame denoising. Noise reduction techniques may be employed to improve the quality of digital video. Frames may be extracted from a video. Synthetic frames may be created using motion data between the extracted frames. Synthetic frames may be masked to exclude pixels from the composite frame. Thresholds used in masking may vary based on the temporal distance of the extracted frame used to create the synthetic frame and the extracted frame. Masking may be based on frame differences between extracted and synthetic frames (e.g., sub-pixel / luminance differences), areas of lower quality motion data (e.g., occlusions), or edge detection in the extracted frames. Synthetic and extracted frames may be composited generating frames having less noise. The composited frame may be based on averaging pixel values across the synthetic and extracted frames. Composited frames may be compiled and encoded into denoised video.

The invention discloses an automobile long-distance speed recognition and tracking method based on target detection, and the method comprises the steps: collecting a vehicle driving video in real time through a fixed camera position and angle, and carrying out the recognition of a vehicle in each frame of image of the video through a pre-trained YOLOv12 target detection model; performing preliminary speed estimation on the automobile by adopting an inter-frame difference method, further constraining a speed change rate, and performing time sequence correction on the speed change rate by adopting Kalman filtering to obtain a corrected speed estimation value; calculating the displacement and the motion deflection angle of the adjacent frames in the transverse and longitudinal directions, and integrating the displacement and the motion deflection angle with the corrected speed estimation value to form a time sequence input feature; and carrying out modeling on a historical track through the trained time sequence deep learning model to realize dynamic speed correction. According to the method, the dependence on physical space calibration is obviously weakened, the perception capability of the model on the motion trend is improved, and the method is suitable for vehicle tracking and speed measurement tasks in long-distance and low-resolution scenes.

The invention relates to a monitoring video stream transmission method and device, equipment and a medium. The method comprises the following steps: acquiring performance parameter data, hardware resource utilization rate data and network condition data of video monitoring equipment and acquired video stream data; calculating a brightness difference in the video stream data by adopting a frame difference method; analyzing the spatial and temporal distribution characteristics of the brightness difference to obtain a motion significance index; determining the priority of video stream transmission according to the motion saliency index; based on the priority, combining the performance parameter data and the hardware resource utilization rate data, and adopting a first preset rule to allocate a video coding strategy for each video monitoring device; and generating a monitoring video stream transmission scheme by adopting a second preset rule according to the video coding strategy, the network condition data and the current hardware resource utilization rate data. According to the invention, the transmission priority and the coding strategy can be dynamically adjusted according to the video content, and the transmission efficiency and the quality stability of the monitoring video stream are improved.

The invention provides an early-stage enteromorpha identification method, medium and system, and belongs to the technical field of enteromorpha identification. According to the early-stage enteromorpha identification method and system, a dynamic feature fusion module based on inter-frame difference is used for extracting time sequence features of continuous frames, cross-modal information integration is achieved through a double-attention multi-modal feature fusion module, an improved YOLOV8 network model is constructed for target detection, and the identification accuracy of the early-stage enteromorpha is improved. Meanwhile, a liquid neural network model is combined with a multiband ratio method and a floating algae exponential function to carry out spectral feature recognition, enteromorpha components in mixed pixels are processed through a sub-pixel decomposition technology, and finally, multi-dimensional information such as the detection confidence coefficient, the spectrum matching degree, the enteromorpha abundance value and the target number is comprehensively analyzed and detected through a decision fusion algorithm. Accurate recognition and positioning of the early enteromorpha are achieved, and the technical problem that accurate recognition and distinguishing of the early enteromorpha are difficult to achieve at present is solved.

The invention discloses a video key frame extraction method based on cover frame difference and a related device, and the method comprises the steps: obtaining cover frames of a to-be-processed video clip, calculating the frame feature value of each cover frame in a cover frame set, calculating the similarity between the cover frames based on the frame feature values, and obtaining the similarity between the cover frames; dividing video clips into a plurality of scene groups according to cover inter-frame similarity, on this basis, calculating inter-frame change degrees of the clips in the scene groups, adaptively determining the number of key frames in each group according to the inter-frame change degrees, and finally selecting key frames which can best represent content change in the scene groups. The calculation cost of the key frame extraction process is obviously reduced, and the frame extraction efficiency is improved.

The present disclosure belongs to the technical field of machine vision, and particularly relates to a tunnel abnormal form identification method and system based on machine vision, which comprises the following steps: acquiring a tunnel scene video to be identified; capturing a previous frame image and a current frame image of the acquired video based on a preset time interval; obtaining a frame difference image by processing the captured previous frame image and current frame image through a frame difference method; and analyzing the running characteristics of the tunnel scene video according to the obtained frame difference image and a preset frame difference threshold image, and identifying the abnormal form in the tunnel. The present disclosure can accurately monitor the abnormal burst form in the tunnel, issue a warning when a hazard occurs, and maximize the safety of the construction in the tunnel.

The application discloses a kind of real-time optical flow detection systems on chip based on frame difference type sensor, including frame counter, buffer array, memory array and on-chip processor, frame counter, for generating the time label of event;Buffer array, for temporarily storing the event output of sensor array;Memory array, for temporarily storing the event data of corresponding pixel position in sensor array, flag bit data and the time label of the event;On-chip processor, for completing the calculation and control of detection system;The application has the advantages that: real-time accurately carries out the estimation of optical flow direction, high precision.

The invention relates to the technical field of video data, and discloses a compression extraction and processing method for key frames in video data, which comprises the steps of input and preprocessing, inter-frame difference score calculation, optical flow motion score calculation, fusion scoring, time sequence smoothing and local extremum screening, redundancy suppression, and key frame compression and index reconstruction. Through the steps of inter-frame difference analysis, optical flow motion field calculation, adaptive fusion scoring, time sequence smooth constraint, redundancy suppression and feature compression encoding, adaptive extraction and compression processing are performed on frames with significant changes or semantic importance in a video sequence, and low-layer change features are obtained through pixel layer frame difference calculation. Capturing local and global motion features through optical flow vector field modeling; constructing a criticality scoring model, carrying out weighted fusion on multi-channel features, carrying out smoothing and extreme value detection on a time dimension, and selecting a most representative video key frame; compression and index structure reconstruction are completed, and structured storage and efficient restoration of video data are achieved.

The invention discloses a GPU (Graphics Processing Unit) parallel hierarchical motion detection method and a GPU parallel hierarchical motion detection system for edge computing. The method comprises the following steps: acquiring multi-channel video stream data, and copying the processed multi-channel video stream data to a GPU (Graphics Processing Unit) according to whether an edge device supports DMA (Direct Memory Access) to match a corresponding data processing strategy; on the GPU, performing global motion filtering on the processed grayscale images of the current frame and the previous frame of video data, obtaining a difference graph through parallel vectorization inter-frame difference, performing tree reduction summation, and calculating to obtain the number of global motion pixels; and judging whether the number of the global motion pixels exceeds a preset threshold value, if so, calculating a motion area of the global motion pixels and positioning a motion target, and otherwise, directly processing a grayscale image of the next frame of video data. According to the invention, the actual demand of large-scale and low-cost edge deployment is met, and the balance among performance, power consumption, cost and compatibility is achieved.

The invention provides a video stream playing and analyzing system and a working method thereof, the system performs video stream media playing and video analysis, and the system comprises a multi-video stream playing module, a multi-channel playing module, a video stream comparison module, a code stream size detection module and a video stream broadcasting module; the method comprises the following steps: S1, acquiring chip channel information; s2, acquiring information of a video stream; basic information of the code stream; s3, according to functions, performing S4 playing, S5 detection and S6 comparison respectively; s4, multi-video playing: playing each video stream; s5, code stream size detection: counting code stream information of 256 frames; respectively displaying the code stream information of each frame and the statistical information of the first 256 frames; s6, video stream comparison: respectively acquiring video stream information of the video A to be detected and the video B to be compared; respectively extracting and displaying images in the two videos; obtaining a video C with a mark after frame difference; judging whether the display end displays A or B; after determining a display video, fusing the video with the C; and displaying the final video.

The application discloses a forklift illegal use monitoring method, medium and equipment based on images, and relates to the technical field of forklift monitoring. Two images captured by a camera at an interval of a first preset time length are acquired; frame difference binarization processing is performed on the two images to obtain a frame difference image; a target minimum circumscribed rectangle is determined for a connected region of the frame difference image; whether a width-length ratio of the target minimum circumscribed rectangle is less than a first preset threshold value is judged for each target minimum circumscribed rectangle; if the width-length ratio is less than the first preset threshold value, it is determined that the target minimum circumscribed rectangle corresponds to a forklift illegal use. Frame difference binarization processing is performed on two images captured by a camera at an interval of a first preset time length to obtain a frame difference image, a target minimum circumscribed rectangle is determined for a connected region in the frame difference image, and whether a forklift illegal use behavior exists is determined according to whether a width-length ratio of the target minimum circumscribed rectangle is less than a first preset threshold value, so that consumption of network resources can be reduced, and labor cost can be lowered.

The invention relates to the technical field of computer vision and industrial safety monitoring, and discloses a video target detection method and system based on a coupling frame difference yolov8 model, and the method comprises the steps: 1, collecting a video stream in real time, extracting an RGB image of a current frame, and converting the RGB image into a gray-scale map; meanwhile, a historical frame grey-scale map cache queue with a fixed length is constructed and maintained and is used for storing grey-scale information of recent frames; step 2, calculating a frame difference between a current frame grey-scale map and a historical frame grey-scale map at an interval of 10 frames in a buffer queue, introducing a space-time coupling causal attention mechanism, and generating a self-adaptive attention weight single-channel frame difference image; 3, taking the single-channel frame difference image as a motion feature channel, and splicing the single-channel frame difference image with the RGB three-channel image of the current frame in the channel dimension to construct a four-channel fusion data tensor; and step 4, training a yolov8 detection model by using the four-channel fusion data, so that the yolov8 detection model can cooperatively utilize static appearance and dynamic motion clues, and a detection result is output.

The invention provides a valve opening and closing operation detection method and an applicable system and a readable medium thereof, and relates to the technical field of computer visual recognition. The detection method comprises the following steps: acquiring a plurality of continuous image frames containing the switch component in a preset time period; frame difference values corresponding to a plurality of continuous moments associated with the plurality of continuous image frames are obtained through calculation according to the pixels of the plurality of continuous image frames; a plurality of image frames before the valve is opened and closed for the first time are selected from the plurality of continuous image frames to serve as static frames; obtaining a starting time threshold value and an ending time threshold value corresponding to the same opening and closing operation according to the frame difference values corresponding to the plurality of static frames; and for a plurality of continuous moments corresponding to each opening and closing operation, taking the continuous moment corresponding to the first frame difference value greater than the starting moment threshold value as the starting moment of the same opening and closing operation, and taking the continuous moment corresponding to the first frame difference value less than the ending moment threshold value after the starting moment as the ending moment of the same opening and closing operation.

The application provides an image detection method and device and a computer readable storage medium. A current image in a video stream is obtained, and a reference image is obtained. The current image is input into a rain removal model to obtain a processed image processed by the rain removal model. A first frame difference image of the current image and the reference image is obtained, and a second frame difference image of the processed image and the reference image is obtained. Difference information of the first frame difference image and the second frame difference image is obtained, and it is determined whether the difference information meets a preset condition. In the manner, whether it is a rainy day can be accurately determined through the difference information of the current image and the current image processed by the rain removal, other factors in the image background can be excluded, the accuracy is improved, misjudgment is prevented, and robustness is improved.

This application discloses an IoT video transmission method, system, device, and medium. The method acquires first IoT video stream data at an edge terminal. The first IoT video stream data includes several first video frames. Inter-frame content analysis is performed on the first IoT video stream data to obtain inter-frame difference data for each first video frame. Based on all inter-frame difference data, dynamic frame extraction is performed on the first IoT video stream data to obtain second IoT video stream data. The second IoT video stream data is sent to a server, whereby the server performs frame interpolation processing on the second IoT video stream data, obtaining third IoT video stream data, which is then sent to the user terminal. This method can effectively reduce IoT video transmission bandwidth while improving the integrity and clarity of video transmission, thereby enhancing the user's video viewing experience. This application relates to the field of IoT technology.

The application provides an image occlusion intelligent detection method and device, which comprises the following steps: based on a video sequence, a frame difference method is used to determine a first continuous N1 frame area without pixel change as an initial background area; the video sequence after the first continuous N1 frame is divided into multiple continuous processing periods; in each processing period, the following steps are executed: based on the video frame in the current processing period, a pixel change area is calculated and the effective background area of the current processing period is updated according to the pixel change area, which is used as the effective background area of the next processing period; a fusion Bhattacharyya distance between the effective background area and a reference frame is calculated; the mean value and the standard deviation of the fusion Bhattacharyya distance corresponding to the processing period of the first N2 video frames in the video sequence are calculated, and an adaptive threshold is calculated according to the mean value and the standard deviation; each fusion Bhattacharyya distance is compared with the adaptive threshold in sequence, and according to the comparison result, it is determined whether the video frame has occlusion. The method and device of the application have low false positive rate, the threshold is self-adjusted, and the determination is accurate.

An intelligent port dynamic background frame difference spilled object real-time detection method comprises the following steps: (1) taking a first frame image of an original video as a reference background image during background difference, and obtaining a foreground image through the frame difference between the images; (2) a foreground object separation detection method based on edge detection is used to distinguish dynamic people or vehicles and spilled objects in the foreground image; (3) the edge is accurate to the single-pixel width through a non-maximum suppression step, an obtained result is processed through closed operation to enable the edge to be closed, and whether the object is a throwing object or not is judged according to the dynamic states and the position size states of different contours; and (4) correcting the contour region based on edge detection through a symmetric difference method to obtain a current instantaneous background, and carrying out background updating on a noise region by adopting a first-order Kalman filter. According to the invention, real-time thrown object identification can be carried out in a specified range without training, and the position of the thrown object can be timely and effectively marked.

The present application belongs to the field of computer vision, and particularly relates to a video anomaly detection method, system and device based on scene classification. The steps of the present application method are as follows: step S1, performing gray processing on original video frames, using background subtraction method and frame difference method to extract foreground targets, and extracting pixel features through Double-Canny algorithm; step S2, using a pre-trained model to detect the number of people in the video frames and generate a heat map of the video frames; step S3, using K-means clustering algorithm to classify scenes of the video frames, and dividing the video frames into two categories of dense scenes and sparse scenes; and step S4, using an anomaly detection module to respectively perform anomaly detection on the dense scenes and the sparse scenes. The present application can select different network structures for anomaly detection according to scenes with different crowd densities, is better applied to complex real scenes, and achieves better anomaly behavior detection effect.

The invention provides a diffusion model calculation method and device based on least square fitting and a hardware unit, and the method comprises the steps: generating differential calculation reference data through a least square fitting method based on cached previous frame input data, a previous frame calculation result and original input data of a current time step; performing structured sparse calculation according to the original input data of the current time step, the differential calculation reference data and the previous frame input data to generate an average error correction amount; on the basis of a linear layer of a diffusion model, the average error correction and differential calculation reference data are calculated to generate current frame data, and a high-similarity differential calculation reference is constructed through least square fitting, so that the quality and the stability of the reference data are improved; according to the method, the dynamic threshold value and the structured sparse calculation are combined, the calculation complexity is remarkably reduced on the premise that the model precision is guaranteed, and efficient and rapid calculation with low delay and low energy consumption can be continuously achieved in a modern diffusion model with the inter-frame difference increased.

The application relates to the technical field of video understanding, and provides a space intelligent dynamic video frame sampling method and system based on question sentence semantics, which can realize paradigm transition from traditional 'passive video sampling' to'semantic active perception'. By analyzing the question sentence semantics in advance and dynamically guiding frame selection by using the cross-modal correlation analysis mechanism of semantic vectors and visual features, the video can be watched with the question, and key information such as the spatial position, action stage, object change and the like focused on by the question can be actively focused. In addition, the application proposes a joint optimization strategy of semantic score, inter-frame difference, diversity and spatiotemporal consistency, so that the final key frame can meet the requirements of high semantic correlation, time sequence coherence and complete spatial coverage. Moreover, the task adaptive mechanism of the application can automatically adjust the sampling strategy according to the question type, so that the sampling process has task sensitivity and intelligent adjustment capability, and has excellent generalization and robustness among different tasks.

The present application relates to the technical field of motion data recovery, and provides a human motion data recovery method and device based on tensor representation, which can better maintain the spatial structure and time structure of the human motion data to be recovered by determining the third-order tensor of the human motion data to be recovered. Considering the time sequence of the human motion data to be recovered, a frame difference regularization term is introduced into the objective function, so that the non-smoothness in the recovery process of the human motion data to be recovered can be avoided. The objective function combines the tensor core norm term of the recovery variable and the frame difference regularization term of the recovery variable, simultaneously considers tensor tube rank minimization and frame difference smoothing, can significantly reduce the recovery error, and obtain a more superior recovery result.

This invention discloses an embedded firmware camera data modification method, apparatus, medium, and device, relating to the field of computer vision technology. The method includes: real-time acquisition of image data and preliminary processing; using frame difference and background modeling algorithms to divide the pre-processed image data into regions and assign priorities, generating a region priority mapping table; extracting feature points of high-priority motion regions in the optimized image data using optical flow, and calculating motion vectors between consecutive frames; triggering an event-driven frame processing mechanism based on the calculated motion vectors between consecutive frames, automatically adjusting the frame rate and processing accuracy; and using the motion vectors extracted by optical flow to calculate the object's motion speed in real time, dynamically adjusting the frame rate and processing accuracy according to the motion speed, ensuring sufficient detail is captured during rapid motion while saving processing resources when stationary.

The application provides a motion history-based foreground background detection method, comprising the following steps: S1, preprocessing: denoising and smoothing, and enhancing the accuracy of frame difference; S2, calculating absolute frame difference; S3, binary processing: diff = absdiff (frame_blurred, prev_frame_blurred); and S4, updating a motion history image MHI. The method can avoid the adverse effects in the prior art, is simple to test, has high testing accuracy, is completely independent, is not interfered by a system, has very small error, and can be completely realized by a software module and is simple to operate.

A kind of similar material model internal stratum change and continuous monitoring method of failure, comprising the following steps: continuous shooting is carried out to monitoring target, and a plurality of time continuous video segments are formed in turn;While video acquisition, key frame extraction is carried out to each video segment collected in turn, and the key frame extracted is saved, and new video dataset is generated, wherein, key frame extraction is carried out to the video segment collected, including the following steps: extracting the key frame index of each image frame in video segment;According to key frame index list L_index, 2 frame difference and 3 frame difference are calculated, and non-key frame is deleted in combination with 2 frame difference and 3 frame difference in video segment, to accurately locate key frame.The design can achieve the effect of real-time shooting, instant processing, accurately obtain the change condition of monitoring target while avoiding a large amount of redundant data.

This invention discloses a method for early warning of hazards during highway high slope construction based on machine vision and deep learning, comprising the following steps: S01, acquiring real-time video data of the construction slope using data acquisition equipment; S02, capturing abnormal situations such as rockfall and rock mass displacement using improved classical algorithms suitable for slopes, such as the frame difference method; S03, providing the construction unit with data on abnormal events for manual backtracking; S04, establishing a backpropagation (BP) neural network using the acquired abnormal data; S05, training the algorithm to autonomously judge early warnings of hazardous situations, such as rockfall, using deep learning technology; S06, using the training results in S05, combined with traditional displacement monitoring algorithms, to jointly issue early warnings for hazardous situations, primarily rockfall and landslides. The method provided by this invention effectively assists construction units in conducting safety assessments and analyses, utilizing machine vision and neural network technologies to provide early warnings of hazardous situations, ensuring the safety of construction personnel and equipment.

The application discloses a kind of black smoke vehicle automatic detection methods based on superpixel segmentation, including steps as follows: obtaining motor vehicle image containing black smoke exhaust and moving shadow, using superpixel segmentation algorithm to obtain classification training sample;Classification model is built based on lightweight network MobileNetV2, and the superpixel image of motor vehicle, black smoke exhaust and moving shadow is input into classification model learning training;Three-frame difference method is used to extract the moving target area of motor vehicle to be measured, and the superpixel segmentation algorithm is used to segment the moving target area image, to obtain the superpixel image input into classification model identification classification;If there is black smoke exhaust superpixel image in classification result, then determine that the motor vehicle is black smoke vehicle and identify its license plate number information.The application is based on the idea of "segmentation-classification", with small detection error, high universality and high accuracy.

The invention provides a static target determination method and device, equipment and a storage medium, and is applied to the field of image processing, and the method comprises the steps: obtaining a first detection frame corresponding to a preliminary dynamic target in a current frame image; the preliminary dynamic target is a target left after static target preliminary filtering is carried out on the current frame image; determining a binary frame difference image between the current frame image and the candidate frame image according to the gray-scale maps corresponding to the current frame image and the candidate frame image; the candidate frame image is an image which is before the current frame image and is spaced from the current frame image by a preset frame number; denoising the binarized frame difference image, and determining whether the initial dynamic target is a static target according to the number of first target pixel points in a region corresponding to a first detection frame in the denoised binarized frame difference image; the first target pixel point is a pixel point of which the pixel value is not zero in the corresponding area of the first detection frame. By adopting the technical scheme of the invention, the accuracy of the determined static target can be improved.

The application claims a thermal power plant smoke and fire detection method based on interframe difference method and improved YOLOv4. First, the main network of the detection model is constructed by parallel DFC attention and residual, and the performance decline caused by a single detection head is jointly made up by using expansion convolution and receptive field supplement block to construct GS-YOLO model. Then, the video frames of smoke and flame accidents in thermal power plants are labeled to obtain a classification labeled data set and data enhancement. Then, GS-YOLO is trained for detecting smoke and fire, and attack noise is added to the network, which will help the network to distinguish the background and the detection target without changing the optimization target of the model. The test set with real labels is used to verify the target detection model, and the model with high detection performance is obtained. In actual detection, the moving part in the video is obtained by interframe difference method, and the irrelevant background image of the input model is reduced. The method has excellent smoke and fire detection performance and fast inference speed.

The present application relates to the technical field of non-contact physiological signal detection, and discloses a remote physiological signal detection method and system based on state space and double-path interaction. The method comprises: obtaining a sample set; performing frame difference preprocessing on an original face video to extract time sequence features; modeling the extracted time sequence features in time sequence dependence through a state space model and a state space duality mechanism; enhancing the time sequence features in a frequency domain through a frequency domain feedforward network; inputting the time sequence features enhanced in the frequency domain into a self-attention path and a cross-attention path respectively, and then fusing the time sequence features processed in the two paths to take the fused data as a predicted rPPG signal; performing model training by minimizing the difference between the predicted rPPG signal and an actual rPPG signal; and inputting a face video of a person to be detected into the trained prediction model to output a corresponding predicted rPPG signal. The detection method has good accuracy and robustness.

This invention relates to a method for detecting the edge of weak moving infrared targets based on frame difference local contrast. The method identifies the main false alarm sources—high-brightness cloud edges, blind flash noise, and the inter-frame radiometric characteristics differences of the target. It enhances the target edge through three-frame temporal difference and an improved local contrast calculation method, removing false alarm sources such as flash noise, high-brightness background, and background edges. Then, based on the generated saliency map, threshold segmentation is used to obtain the target edge detection result, and finally, the original image is retrieved to obtain the final accurate target location. This invention addresses the difficulty in simultaneously meeting the requirements of detection rate and false alarm rate for weak infrared targets under complex dynamic backgrounds in practical engineering. Experimental results show that the proposed algorithm has high stability, effectively reducing the number of false alarms and improving target detectability while ensuring detection efficiency.