69 results about "Salient objects" patented technology

The invention relates to the technical field of light field image salient target detection, in particular to a light field salient target detection method based on edge perception and hierarchical fusion, and the method comprises the steps: carrying out the multi-scale feature extraction of a focus stack image and a full-focus image through a backbone network; performing edge fusion enhancement on the focus stack features of four layers of different scales through an SEPM module and an EFM module; fusing high-level multi-modal semantic information from the global and local aspects by using an LHFM module; fusing low-layer space information and refining a salient target by using an LLFM module; and aggregating multi-scale information of a high layer and a low layer, and decoding the multi-scale information into an accurate saliency prediction image by using a detection head. According to the method, edge perception and a lightweight hierarchical fusion strategy are combined, the model parameter quantity and the calculation complexity are remarkably reduced while the high detection performance is kept, and the optimal balance between the performance and the efficiency is achieved.

The invention discloses an RGB-D salient target detection method based on decoupling contrast learning, and designs a saliency detection framework integrating expression enhancement, modal collaborative perception and structural discrimination learning by combining a structural heterogeneity problem in multi-modal modeling and utilizing the frequency domain structural advantage of a deep mode and the long-distance modeling capability of Transform. By introducing wavelet convolution and Transform joint modeling, a cross-modal interaction parallel fusion mechanism and a pixel-level structure perception contrast learning strategy, high-precision, multi-scale and boundary clear detection of a salient target area in a complex scene is realized. The method can effectively solve the problems of large information difference between modes of the RGB and the depth map, difficulty in structure alignment, fuzzy boundary prediction, weak feature expression ability and the like, significantly improves semantic consistency and structural integrity of the salient region, and has good cross-modal generalization ability and robustness.

The invention discloses a saliency target detection method based on a Mama network two-way guidance model. The method comprises the steps that a two-way model framework based on the Mama network is composed of an encoder branch, an edge branch, a saliency branch and a decoder branch; the encoder branch performs block division on the obtained original image to be detected, inputs the image to the Mama feature extractor and performs down-sampling to obtain five-layer features, the first three-layer low-layer features are respectively subjected to convolution processing and then are used as edge features to be input into the edge branch, the first four-layer features are used as significant features to be input into the significant branch, and the significant branch is used as edge features to be input into the edge branch; the fifth-layer high-level features are subjected to two-stage mixed attention processing, global features are obtained, and positioning guidance is provided for subsequent feature fusion; the edge branch performs receptive field expansion and spatial enhancement on the input edge features to obtain edge fusion features. According to the invention, the precision and efficiency of saliency target detection can be well improved.

An example method includes generating, at a heat map generation frequency, one or more saliency heat maps associated with a video of a scene being captured by an image capturing device. The method also includes detecting, based on the one or more saliency heat maps, a salient object in the scene. The method additionally includes responsive to the detecting of the salient obj ect: initiating a tracking of a region of interest (ROI) associated with the salient object in subsequently captured video of the scene, and reducing the heat map generation frequency for generation of saliency heat maps for the subsequently captured video of the scene. The method also includes adjusting, based on the tracked ROI, an automatic image capture setting of the image capturing device.

This invention relates to a weakly supervised video salient object detection method and system based on memory-edge guidance, belonging to the field of object detection technology. It includes: dividing a given long video sequence into non-overlapping sliding windows to extract several consecutive video frames; inputting these video frames into a trained memory-edge guidance network model to achieve weakly supervised video salient object detection; specifically, it includes: extracting features from consecutive video frames at the current time step to obtain spatiotemporal features extracted at different scales; using salient cues mined from historical frames to enhance the semantic representation of relevant objects in the current frame; and then inputting these features into a decoder to obtain the final salient object detection map. This invention achieves accurate localization and fine segmentation of salient objects in videos.

The invention discloses a salient target rapid positioning method for an electric power visual model, which belongs to the technical field of electric power system inspection, processes image data of electric power communication equipment through a deep learning algorithm, performs feature extraction and classification by adopting a convolutional neural network (CNN), and identifies abnormal conditions of salient targets in an electric power system in real time. Therefore, accurate positioning and detection of the target are realized. Through an integrated edge calculation method, the system can complete primary processing and analysis of image data on intelligent terminal equipment. Therefore, the delay of data transmission is reduced, and the response speed of target positioning and detection is improved. And the real-time requirement is met, so that the system can quickly respond in a complex electric power inspection environment, and the system is suitable for field inspection and equipment state monitoring of an electric power system. A high-quality electric power visual data set is constructed by integrating operation data of various devices such as an electric power transmission network, a transformer substation and the like, historical inspection data and sensor data.

The present application provides an image processing method, device and equipment, which can be applied to the technical field of image processing. The image processing method comprises: pre-processing an input image to obtain input features; inputting the input features into a visual encoder and a multi-layer perception machine in a visual center decoupler respectively to obtain enhanced special features and salient object detection special features; the visual encoder aggregates local region features based on the input features to obtain the enhanced special features, and the multi-layer perception machine captures edge information based on the input features to obtain the salient object detection special features; inputting the enhanced special features into an enhancement network to obtain enhanced output features; the enhancement network takes illumination weights of different color channels and local binary pattern features of the input image as illumination constraints, and enhances the enhanced special features to obtain the enhanced output features; and inputting the salient object detection special features and the enhanced output features into a salient object detection network to detect a salient object.

The present application relates to a kind of full supervision's salient object detection method, constructs complete multi-branch feature fusion refinement network MFFRNet as salient object detection model;Again training set in data set is input to the proposed MFFRNet model training, every time completing a round will be back propagated once, to optimize MFFRNet model parameter;With data set test set, the performance of model is evaluated;Finally, the model after evaluation is used for salient object detection.The model effectively fuses the detail information of low-level feature and the semantic information of high-level feature.The module designed for low-level feature utilizes asymmetric convolution to reduce background noise and other interference factors, and a module designed for high-level feature obtains rich semantic information.Meanwhile, aliasing effects caused by frequent up-sampling are effectively handled.The method effectively captures salient objects and obtains saliency prediction map, and has strong robustness.

A method and an electronic apparatus for performing unified segmentation of media content are provided. The method includes: determining a guidance map for an input frame based on a salient object from a past frame output mask and user-interacted objects in the media, operating in either salient mode or selective mode. The input frame of the media is cropped based on the guidance map and the salient ROIs of the salient object. A weighted grayscale image of the cropped frame is generated from the past frame output mask. A fused spatio-color mesh grid representation of the cropped frame in YUV format is determined. The cropped image frame, along with the weighted grayscale image and the fused spatio-color mesh grid representation, is input into a segmentation model. The segmentation model generates either a salient object segmentation or a user-interacted object segmentation for the media.

The application discloses an RGB-D salient object detection method based on boundary deformable convolution guidance, comprising the following steps: step one, respectively extracting features of an RGB mode and a depth map mode; step two, fusing the features of the two modes through a cross-modal attention fusion feature module to mine common and complementary features of salient objects; step three, inputting the feature map into an encoder deep layer embedded with an adjacent multi-scale feature enhancement module to obtain global context feature information; step four, generating a boundary clue map of the salient objects by constructing a boundary feature extraction module; and step five, generating a saliency map by using the generated boundary clue map and deformable convolution guidance. The application mines and strengthens the commonness of salient objects by cross-fusion of the depth map and the RGB image, effectively captures salient objects with different sizes and uncertain quantities by using adjacent level feature interaction, and solves the boundary blur problem of the saliency map by using the edge clue map to guide the model decoding.

This invention discloses a method for detecting salient objects with a partial-object relationship based on disentangled capsule routing, comprising: extracting basic deep features from an input image to obtain basic deep features at five different scales; further extracting multi-receptive field deep features from the basic deep features; utilizing a pre-trained capsule network based on a disentangled routing algorithm to analyze the deep features at three deep scales to obtain corresponding partial-object relationship features; fusing the corresponding partial-object relationship features with the deep features to obtain a fused feature at three deep scales; and further fusing the deep features at the first and second scales and the fused feature at three deep scales to obtain a fused feature, and generating a saliency map based on the fused feature. This invention solves the problems of the existing techniques, such as the large number of network parameters and slow inference speed, by achieving better foreground and background segmentation and faster network inference speed. It can be used in image preprocessing in computer vision.

A method of performing saliency segmentation for a preview image frame, including: receiving the preview image frame from an imaging unit, generating a plurality of saliency boxes including one or more salient subjects, for each of a plurality of subjects in the preview image frame, selecting, from among the plurality of saliency boxes, a set of saliency boxes including a first set of salient subjects based on a ranking of each saliency box from among the plurality of saliency boxes, and extracting one or more salient images along with boundary information corresponding to each salient subject from among the first set of salient subjects.

The invention discloses a saliency object detection method, device and equipment, and belongs to the technical field of image processing. The saliency object detection method comprises the following steps: acquiring a first image; dividing the first image into a plurality of color areas according to the pixel values of the pixel points in the first image; wherein the pixel value similarity of the pixel points in the same color area is greater than or equal to a pixel value similarity threshold; extracting at least one feature of each color area; determining a contrast of the first color region relative to the first feature; wherein the first color region is any one color region in the plurality of color regions, and the first feature is any one feature in the at least one feature; determining a histogram contrast of the first color region; determining a first comprehensive contrast ratio of the first color area according to the contrast ratio of the first color area relative to the first feature and the histogram contrast ratio of the first color area; and determining a salient object in the first image according to the first comprehensive contrast of the plurality of color regions.

The application provides a video salient object detection method based on spatio-temporal context scene relationship propagation, and relates to the technical field of video salient object detection. First, scene analysis is performed on each frame of video in a video frame sequence to obtain an instance-level object corresponding to each frame of video. Then, global instance-level features, local instance-level features and intra-frame low-level features of each frame of video and the corresponding instance-level object are extracted. Then, a matching frame of any frame of video is randomly sampled from the same video frame sequence, global instance-level features of the matching frame are extracted, the global instance-level features are integrated into global instance-level features of the matching frame, and time features between video frames are obtained. The dense spatial attention mechanism is used to integrate the local instance-level features into the global instance-level features to obtain spatial features. The time features and the spatial features are spliced to obtain spatio-temporal features. The spatio-temporal features and the global instance-level features are input into a convolutional neural network based on a gated recurrent unit for updating to obtain high-level spatio-temporal features. Finally, the intra-frame low-level features and the high-level spatio-temporal features are fused and decoded to generate a video salient object mask detection result. The application utilizes rich inter-frame and intra-frame scene relationship information in the video, and improves the accuracy of video salient object detection in complex scenes.

The application provides a flotation froth stability estimation method based on infrared time sequence significant target segmentation. First, a U-shaped network based on a ConvNeXt network design is used, a ConvLSTM network is embedded in the encoder to realize time sequence infrared saliency information extraction, and a cross attention mechanism is added to the ConvNeXt network to realize initial positioning of the infrared saliency area. Second, a residual refinement network with a U-shaped encoder-decoder structure is constructed, the residual between the deep learning saliency map and the true value is learned to improve the edge details of the saliency area, and fine segmentation of the time sequence significant target is realized. Finally, according to the significant target segmentation result, the froth stability is calculated, the deviation and abnormal threshold of the froth stability in the time sequence under different working conditions are counted, the significant area of the froth infrared video image is detected to realize the segmentation of the merged and broken bubbles, and the froth stability is evaluated according to the segmentation result.

A method and an electronic apparatus for performing unified segmentation of media content are provided. The method includes: determining a guidance map for an input frame based on a salient object from a past frame output mask and user-interacted objects in the media, operating in either salient mode or selective mode. The input frame of the media is cropped based on the guidance map and the salient ROIs of the salient object. A weighted grayscale image of the cropped frame is generated from the past frame output mask. A fused spatio-color mesh grid representation of the cropped frame in YUV format is determined. The cropped image frame, along with the weighted grayscale image and the fused spatio-color mesh grid representation, is input into a segmentation model. The segmentation model generates either a salient object segmentation or a user-interacted object segmentation for the media.

This application provides a method for detecting salient objects in images. It constructs a detection model based on a lightweight Mobilenetv2 backbone network and introduces fusion side connections into this backbone network to progressively fuse features from each layer. The method predicts salient objects at multiple scales and performs supervised learning, effectively avoiding overfitting. The proposed method constructs a lightweight detection model, and by introducing fusion side connections, it fully integrates features from each layer, making the model's performance comparable to larger existing models. The lightweight and high-performance detection model constructed in this application is suitable for deployment on television terminals and can be applied to television application scenarios such as visual object tracking and intelligent picture quality settings.

A system may access an input image. The system may generate a plurality of segments based on one or more segmentation models and the input image, each segment from among the plurality of segments representing a corresponding salient object. The system may generate a depth map based on a depth estimation model. The system may layer the plurality of segments, based on the depth map and border regions between pairs of segments, to generate a plurality of ordered segments. The system may execute a vision-language model to generate a text annotation of the image based on the plurality of ordered segments.

The present disclosure relates to the technical field of target detection, and proposes a parabola detection method and system based on human local binary feature point alignment, which comprises the following steps: acquiring a continuous frame image to be detected, calibrating key feature points of a pedestrian in an image based on local binary features of pixel points, forming shape contours of each part of the pedestrian according to the key feature points, and judging whether the pedestrian makes a throwing action and the type of the throwing action according to the relative positions of the center points of each part of the human body; when a throwing action of the pedestrian in the image is recognized, taking the center point of the trunk of the pedestrian as a reference, and determining a possible area of a thrown object according to the type of the throwing action of the pedestrian; and detecting the throwing of the object by the pedestrian by using a salient object detection method according to pixel context information, and determining that the pedestrian throws an object when making a throwing action if the object is detected. The present disclosure simultaneously uses the method of salient object recognition to detect and track the thrown object based on the alignment of human local binary feature points, thereby improving the accuracy of parabola detection.

The application discloses a salient object ranking method based on visual prior knowledge, constructs a salient object ranking network in an offline stage, and is used for identifying each salient object in an image and generating a result based on target salient object ranking after training based on a data set of visual prior knowledge. The application can automatically generate a salient object ranking result conforming to human objective observation rules and generalization, and provides more practical technical support for the application of intelligent auxiliary tools for visually impaired patients, controllable image description generation, human-computer interaction, auxiliary decision, intelligent monitoring, automatic driving, augmented reality and the like.

The application provides a kind of synergistic salient object detection method and storage medium, the method is realized by salient feature enhancement and global information guidance, constructs synergistic salient object detection model, in down-sampling network, image feature is extracted by VGG16 backbone network, and the saliency of image feature is enhanced using coordination attention module, and dynamic convolution collaborative search module is used to search common salient object feature as synergistic feature, in up-sampling network, receptive field inflation technology is used to increase receptive field, and long-distance dependence information of image is obtained by non-local module, to optimize synergistic feature, and as the input of global information guidance fusion module, to reduce non-salient background interference. Finally, the whole synergistic salient object detection model is optimized by loss function. The method is fast in operation, and the final synergistic salient object prediction result is complete in structure and accurate in target.

The present disclosure relates to systems, method, and computer readable media that iteratively apply a neural network to a digital image at a reduced resolution to automatically identify pixels of salient objects portrayed within the digital image. For example, the disclosed systems can generate a reduced-resolution digital image from an input digital image and apply a neural network to identify a region corresponding to a salient object. The disclosed systems can then iteratively apply the neural network to additional reduced-resolution digital images (based on the identified region) to generate one or more reduced-resolution segmentation maps that roughly indicate pixels of the salient object. In addition, the systems described herein can perform post-processing based on the reduced-resolution segmentation map(s) and the input digital image to accurately determine pixels that correspond to the salient object.

This application discloses a training method, apparatus, electronic device, and computer-readable storage medium for a video salient object detection model. Addressing the issues of insufficient multimodal fusion, temporal instability, and high label dependence, a two-stage training framework is proposed: The first stage uses cross-modal unsupervised contrastive learning to mine consistency and complementarity information between RGB and deep modalities, generating and iteratively optimizing salient object pseudo-labels to improve their quality; the second stage uses the optimized salient object pseudo-labels as supervision signals, selecting historical frames and adjacent frames to construct a reference set, training the target model through temporal feature fusion, and iteratively updating network parameters, enabling the model to obtain a stable representation in the time dimension, enhancing its ability to model long-term and short-term dependencies, suppressing dynamic interference, and maintaining target continuity. This method eliminates the need for manually labeled data, effectively reducing data costs through cross-modal contrastive learning and temporal feature fusion, while improving detection accuracy and robustness in complex scenes.

This invention provides an evolutionary and inherited method for detecting salient objects in high-resolution drone imagery, belonging to the field of image processing technology. The method comprises an evolutionary phase and an inheritance phase. The evolutionary phase uses evolutionary mechanisms at both the supervisory and feature levels to achieve detail-preserving and target-integrity salient object localization in low-resolution images. The inheritance phase utilizes shallow high-resolution features to supplement and enhance inherited features in a lightweight manner, generating a final high-resolution salient prediction. The invention achieves higher-precision salient object detection in high-resolution drone imagery.

Disclosed frameworks for generating an image including a salient object and a staged background include extracting a salient object from a source image and applying a generative model to the salient object to generate the image. According to some embodiments, extracting a salient object from a source image involves using salient object detection method to identify the relevant portions of the source image corresponding to the salient object. In some embodiments, the generative model is a generative adversarial network trained using a domain relevant dataset.

The application discloses a salient object detection method and device. After obtaining a to-be-detected image, the application extracts RGB features and depth features of the to-be-detected image through an encoder; the application respectively performs feature enhancement on high-level features of the RGB and depth through an attention feature enhancement module; the application inputs the extracted RGB features and depth features into a cross-modal fusion module to strengthen and fuse the RGB features and depth features; the application generates edge information of salient objects in the depth features by using an edge extraction module; the application inputs the strengthened and fused RGB features and depth features into a multi-scale feature aggregation module to perform multi-scale feature aggregation and obtain multi-level fusion features; the application inputs the multi-level fusion features into a cascaded correction decoder to refine and correct the multi-level fusion features, predict salient features, and then enhance the salient features by using the edge information to generate a saliency map; and the application breaks the limitations of the prior art in global context modeling and multi-scale feature aggregation.

The invention discloses an RGB-T image saliency object detection method based on a Mama feedback iterative network, and belongs to the field of computer vision. According to the network, a Mama encoder with double branches is adopted to extract multiple scales of features; then, a cross-layer feature fusion module is used for integrating features of a subsequent layer and features of a current layer, so that cross-scale correlation among multi-scale features extracted by Mama is enhanced, and significance performance of significant objects under different scales is enhanced; after cross-layer feature fusion, the feature enhancement module is then used for further extracting salient object information and increasing the proportion of salient features in a feature space; after the two modals are processed through the feature enhancement module to obtain refined features, the multi-modal feature fusion module combines the corresponding features in each layer to generate fused features, so that stronger semantics and details are shown; and finally, the generated features are sent to a feedback iteration architecture for two additional iterations to generate a clearer and more complete saliency map. The method is used for solving the common problems of feature detail loss, serious noise interference, poor physical consistency and the like of the saliency object detected in the prior art.

This invention discloses a salient object detection method based on a multi-scale dilated convolutional neural network. The method includes: extracting multi-scale features from the input image; inputting the multi-scale features into a dilated residual convolutional module to obtain fused features including contextual information of the multi-scale features; inputting the fused features into multiple channel attention modules to obtain multiple salient features; performing dimensionality reduction activation on each salient feature to generate a saliency map; and performing deep supervised training using a hybrid loss function that combines cross-entropy and cross-union loss. The method of this invention, based on a multi-scale dilated convolutional neural network, fully captures rich global and local semantic information in the image by using a dilated residual convolutional module, solving the problem of shallow encoder depth and insufficient information extraction. Simultaneously, the designed channel attention modules enable the network to focus on the target region, effectively improving the accuracy of object detection.

The invention provides a saliency target detection method, device and system and electronic equipment, and belongs to the field of computer vision. The method comprises the following steps: acquiring a first visible light image and a first thermal infrared image of a to-be-detected object; inputting the first visible light image and the first thermal infrared image into a pre-trained first model to obtain a first saliency target image of the to-be-detected object; the first model is an image fusion neural network model determined based on a second visible light image and a second thermal infrared image of the training object; the first model comprises a self-adaptive enhancement module, a coding and fusion module and a three-stream differential cooperative decoder. In conclusion, the technical scheme provided by the invention can progressively solve the technical problems of low detection precision, weak anti-interference capability, poor fusion effect and the like of the existing method layer by layer from three core links of input enhancement, feature fusion and decoding collaboration, improves the precision of saliency target detection, and can adapt to various application scenes.

The invention provides an integrated imaging 3D salient target detection method in a low-light environment, and the method comprises four processes: obtaining four-dimensional light field data, recovering low-illumination light field information, carrying out the saliency detection process on a recovered micro-image array, and carrying out the three-dimensional reconstruction of a salient micro-image array, and comprises the steps: reconstructing the four-dimensional light field data into the micro-image array, and carrying out the three-dimensional reconstruction of the salient micro-image array. Based on a low-light vision theory, introducing a complementary illumination map, converting a traditional division method into multiplication and combining with a diffusion model for denoising to realize light field information recovery in a low-light environment, then dividing and recombining a micro-image array into a sequence, taking the sequence as input of a low-light salient target detection model, and combining with a depth and breadth attention module to realize low-light salient target detection. A salient micro-image array is generated through processing of a multi-head attention mechanism, a multi-layer sensor and the like, and finally texture information is recovered and a three-dimensional salient object is reconstructed by means of a lens array. According to the method, the low-light space scene salient target detection precision is effectively improved, and a solution is provided for three-dimensional perception application in a complex environment.