Interval Type-2 (IT2) fuzzy systems have gained significant attention due to their strong capability in handling system uncertainties. This paper investigates the robust stability analysis of conventional Takagi–Sugeno (TS) IT2 fuzzy systems under an observer-based control framework. A non-uniform piecewise linear approximation method is introduced to more accurately capture the boundary characteristics of IT2 membership functions (MFs), allowing key variation information of MFs to be effectively exploited. Subsequently, an error model transformation strategy is proposed to reconstruct approximation-induced errors into an auxiliary fuzzy model, enabling richer error-related and MF information to be explicitly incorporated into the stability conditions and thereby reducing conservatism. By leveraging Lyapunov stability theory and a scaling approach, sufficient stability criteria are derived in terms of linear matrix inequalities (LMIs), which can be efficiently solved using standard convex optimization tools. Simulation results and comparative studies demonstrate that the proposed method achieves less conservative stability conditions and enhanced robustness compared with existing approaches.

In structured light systems, the accuracy of measurement notably diminishes when assessing complex texture objects, especially encountering boundaries between various colors. To address this challenge, this paper meticulously analyzes and establishes an error model, elaborating the correlation between phase errors and the gradients of phase and gray-scale. Based on this analysis, a novel high-precision method is proposed for measuring complex texture objects via bidirectional fringe projection. This approach firstly leverages horizontal and vertical fringe projections to derive bidirectional phase information and calculates the angles between the tangent of the texture edges and the phase gradient. Subsequently, a refined temporal phase correction algorithm is formulated based on the epipolar matching algorithm and the devised error model, effectively mitigating numerical instability issues within the algorithm and significantly reducing errors of bidirectional phases. Ultimately, corrected point clouds are calculated based on bidirectional phases, and the obtained point clouds are merged to further diminish phase errors. Comparison experiments indicate that this method can reduce Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) by 65.74% and 67.75%, respectively. Compared to existing methods, it improves performance by 27.29% and 33.74%, respectively, demonstrating superior performance.

With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning OOD from point annotations has gained great attention. In this paper, we rethink this challenging task setting with the layout among instances and present Point2RBox-v2. At the core are three principles: 1) Gaussian overlap loss. It learns an upper bound for each instance by treating objects as 2D Gaussian distributions and minimizing their overlap. 2) Voronoi watershed loss. It learns a lower bound for each instance through watershed on Voronoi tessellation. 3) Consistency loss. It learns the size/rotation variation between two output sets with respect to an input image and its augmented view. Supplemented by a few devised techniques, e.g. edge loss and copy-paste, the detector is further enhanced. To our best knowledge, Point2RBox-v2 is the first approach to explore the spatial layout among instances for learning point-supervised OOD. Our solution is elegant and lightweight, yet it is expected to give a competitive performance especially in densely packed scenes: 62.61%/86.15%/34.71% on DOTA/HRSC/FAIR1M.

The coded-aperture snapshot spectral imaging (CASSI) system has garnered significant attention as a promising spectral snapshot-based imaging technique. However, several challenges persist in the development of CASSI systems: 1. High hardware costs. 2. The difficulty of balancing the performance and computational efficiency of the reconstruction network. In this paper, we propose a dual-camera mask-free CASSI system to replace the expensive encoding hardware, thereby reducing the overall cost of CASSI. To address the issues of a high number of parameters and computational demands associated with Transformer-based methods, we design a hierarchical attention-based spectral-spatial transformer. This approach involves embedding local features on both the spectral and spatial channels, while also leveraging global information from these channels to enhance the network’s global learning capabilities. Our experimental results demonstrate the superiority of the mask-free approach, achieving a PSNR of 37.9 dB in a single camera and 44.7 dB in dual cameras. Furthermore, experiments indicate that the mask-free system outperforms state-of-the-art methods while requiring lower computational and memory costs.

Accurately estimating the orientation of visual objects with compact rotated bounding boxes (RBoxes) has become a prominent demand, which challenges existing object detection paradigms that only use horizontal bounding boxes (HBoxes). To equip the detectors with orientation awareness, supervised regression/classification modules have been introduced at the high cost of rotation annotation. Meanwhile, some existing datasets with oriented objects are already annotated with horizontal boxes or even single points. It becomes attractive yet remains open for effectively utilizing weaker single point and horizontal annotations to train an oriented object detector (OOD). We develop Wholly-WOOD, a weakly-supervised OOD framework, capable of wholly leveraging various labeling forms (Points, HBoxes, RBoxes, and their combination) in a unified fashion. By only using HBox for training, our Wholly-WOOD achieves performance very close to that of the RBox-trained counterpart on remote sensing and other areas, significantly reducing the tedious efforts on labor-intensive annotation for oriented objects.

To address the problem of robust stability analysis for interval type-2 fuzzy systems (IT2FSs), this paper proposes an innovative analysis approach based on model transformation. Firstly, a classical piecewise linear approximation method is utilized to process the upper boundary membership functions (UMFs) and lower boundary membership functions (LMFs) of the footprint of uncertainty (FOU) in IT2FSs, resulting in linear boundary membership functions (MFs) that are more convenient for analysis, along with the corresponding approximation error functions. Subsequently, a novel error model transformation method is introduced to handle these error terms. By constructing new fuzzy rules and MFs, the boundary error terms are converted into a new fuzzy model, thereby incorporating more information about the error functions into the stability analysis. Based on this model, a robust stability condition in the form of linear matrix inequalities (LMIs) are derived, achieving improved robustness. Finally, the effectiveness of the proposed method is validated through simulations on real-world systems, and its superiority is demonstrated by comparison with existing methods.

With the rapidly increasing demand for oriented object detection (OOD), recent research involving weakly-supervised detectors for learning rotated box (RBox) from the horizontal box (HBox) has attracted more and more attention. In this paper, we explore a more challenging yet label-efficient setting, namely single point-supervised OOD, and present our approach called Point2RBox. Specifically, we propose to leverage two principles: 1) Synthetic pattern knowledge combination: By sampling around each labeled point on the image, we spread the object feature to synthetic visual patterns with known boxes to provide the knowledge for box regression. 2) Transform self-supervision: With a transformed input image (e.g. scaled/rotated), the output RBoxes are trained to follow the same transformation so that the network can perceive the relative size/rotation between objects. The detector is further enhanced by a few devised techniques to cope with peripheral issues, e.g. The anchor/layer assignment as the size of the object is not available in our point supervision setting. To our best knowledge, Point2RBox is the first end-to-end solution for point-supervised OOD. In particular, our method uses a lightweight paradigm, yet it achieves a competitive performance among point-supervised alternatives, 41.05%/27.62%/80.01% on DOTA/DIOR/HRSC datasets.

3D pose transfer over unorganized point clouds is a challenging generation task, which transfers a source’s pose to a target shape and keeps the target’s identity. Recent deep models have learned deformations and used the target’s identity as a style to modulate the combined features of two shapes or the aligned vertices of the source shape. However, all operations in these models are point-wise and independent and ignore the geometric information on the surface and structure of the input shapes. This disadvantage severely limits the generation and generalization capabilities. In this study, we propose a geometry-aware method based on a novel transformer autoencoder to solve this problem. An efficient self-attention mechanism, that is, cross-covariance attention, was utilized across our framework to perceive the correlations between points at different distances. Specifically, the transformer encoder extracts the target shape’s local geometry details for identity attributes and the source shape’s global geometry structure for pose information. Our transformer decoder efficiently learns deformations and recovers identity properties by fusing and decoding the extracted features in a geometry attentional manner, which does not require corresponding information or modulation steps. The experiments demonstrated that the geometry-aware method achieved state-of-the-art performance in a 3D pose transfer task. The implementation code and data are available at https://github.com/SEULSH/Geometry-Aware-3D-Pose-Transfer-Using-Transformer-Autoencoder .

With vigorous development e.g., in autonomous driving and remote sensing, oriented object detection has gradually been featured. The majority of existing methods directly perform regression on the rotation angle, which we argue has fundamental limitations of boundary discontinuity (even if using Gaussian or RotatedIoU-based losses). In this paper, a novel angle coder named phase-shifting coder (PSC) is proposed to address this issue. Different from another well-explored alternative i.e., angle classification, PSC achieves boundary-discontinuity-free in a continuous and differentiable manner and thus can work together with Gaussian or RotatedIoU-based methods to further boost their performance. Moreover, by rethinking the boundary discontinuity of elongated and square-like objects as rotational symmetry of different cycles, a dual-frequency version (PSCD) is proposed to accurately predict the orientation of both types of objects. Visual analysis and extensive experiments on several popular backbone detectors and datasets demonstrate the effectiveness and the potentiality of our approach. When facing scenarios requiring high-quality bounding boxes, the proposed methods are expected to give a competitive performance.

3D multi-object tracking methods utilize object motion, image, and point cloud information to compute similarities between different objects, facilitating cross-frame data association. In this letter, we propose a novel approach called mmMCL3DMOT to calculate object appearance similarity by employing multi-modal momentum contrastive self-supervised learning. We introduce three key techniques. First, a self-supervised training paradigm is adopted, incorporating image, point cloud, and existing 3D detection inputs to enable multi-modal feature extraction without manual annotation. Second, our feature learning approach combines intra-modal and cross-modal feature correspondences within image and point cloud modalities, resulting in more discriminative feature extraction with momentum contrast. Finally, by computing similarity using the multi-modal features and incorporating a robust motion metric, we enable joint cascade reasoning for object association, leading to high-performance 3D MOT. Extensive experiments have demonstrated the significant impact of our method. Moreover, our tracker achieves state-of-the-art (SOTA) performance on both the KITTI and nuScenes datasets.

3D reconstruction is a fundamental task in robotics and AI, providing a prerequisite for many related applications. Fringe projection profilometry is an efficient and non-contact method for generating 3D point clouds out of 2D images. However, during the actual measurement, it is inevitable to experiment with translucent objects, such as skin, marble, and fruit. Indirect illumination from these objects has substantially compromised the precision of 3D reconstruction via the contamination of 2D images. This paper presents a fast and accurate approach to correct for indirect illumination. The essential idea is to design a highly suitable network architecture founded on a precise error model that facilitates accurate error rectification. Initially, our method transforms the error generated by indirect illumination into a sine series. Based on this error model, the multilayer perceptron is more effective in error correction than traditional methods and convolutional neural networks. Our network was trained solely on simulated data but was tested on authentic images. Three sets of experiments, including two sets of comparison experiments, indicate that the designed network can efficiently rectify the error induced by indirect illumination.

Fringe projection profilometry is a widely used technique for 3D measurement due to its high accuracy and speed. However, the accuracy significantly decreases when measuring complex texture objects, especially in the junction of different colors. This paper analyzes the causes of errors resulting from complex textures and proposes a height compensation method to revise the error by employing a dual-projector structure. Moreover, the dual-projector is capable of acquiring a pair of errors with opposite signs, which can be utilized to calculate the accurate 3D information after determining the ratio of this pair of errors. Experiments provide significant improvement in measuring complex texture objects, demonstrating the proposed method's ability.

With the vigorous development of computer vision, oriented object detection has gradually been featured. In this paper, a novel differentiable angle coder named phase-shifting coder (PSC) is proposed to accurately predict the orientation of objects, along with a dual-frequency version (PSCD). By mapping the rotational periodicity of different cycles into the phase of different frequencies, we provide a unified framework for various periodic fuzzy problems caused by rotational symmetry in oriented object detection. Upon such a framework, common problems in oriented object detection such as boundary discontinuity and square-like problems are elegantly solved in a unified form. Visual analysis and experiments on three datasets prove the effectiveness and the potentiality of our approach. When facing scenarios requiring high-quality bounding boxes, the proposed methods are expected to give a competitive performance. The codes are publicly available at https://github.com/open-mmlab/mmrotate.

With the rapidly increasing demand for oriented object detection, e.g. in autonomous driving and remote sensing, the recently proposed paradigm involving weakly-supervised detector H2RBox for learning rotated box (RBox) from the more readily-available horizontal box (HBox) has shown promise. This paper presents H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection. Specifically, we propose to leverage the reflection symmetry via flip and rotate consistencies, using a weakly-supervised network branch similar to H2RBox, together with a novel self-supervised branch that learns orientations from the symmetry inherent in visual objects. The detector is further stabilized and enhanced by practical techniques to cope with peripheral issues e.g. angular periodicity. To our best knowledge, H2RBox-v2 is the first symmetry-aware self-supervised paradigm for oriented object detection. In particular, our method shows less susceptibility to low-quality annotation and insufficient training data compared to H2RBox. Specifically, H2RBox-v2 achieves very close performance to a rotation annotation trained counterpart -- Rotated FCOS: 1) DOTA-v1.0/1.5/2.0: 72.31%/64.76%/50.33% vs. 72.44%/64.53%/51.77%; 2) HRSC: 89.66% vs. 88.99%; 3) FAIR1M: 42.27% vs. 41.25%.

When obtaining three-dimensional (3D) face point cloud data based on structured light, factors related to the environment, occlusion, and illumination intensity lead to holes in the collected data, which affect subsequent recognition. In this study, we propose a hole-filling method based on stereo-matching technology combined with a B-spline. The algorithm uses phase information acquired during raster projection to locate holes in the point cloud, simultaneously extracting boundary point cloud sets. By registering the face point cloud data using the stereo-matching algorithm and the data collected using the raster projection method, some supplementary information points can be obtained at the holes. The shape of the B-spline curve can then be roughly described by a few key points, and the control points are put into the hole area as key points for iterative calculation of surface reconstruction. Simulations using smooth ceramic cups and human face models showed that our model can accurately reproduce details and accurately restore complex shapes on the test surfaces. Simulation results indicated the robustness of the method, which is able to fill holes on complex areas such as the inner side of the nose without a prior model. This approach also effectively supplements the hole information, and the patched point cloud is closer to the original data. This method could be used across a wide range of applications requiring accurate facial recognition.

A newly developed calibration algorithm for camera-projector system using spheres is presented in this paper. Previous studies have exploited image conics of sphere to calibrate the camera, whereas this approach can be strengthened to apply in the projector and ultimately achieve the overall calibration for single or multiple pairs of camera-projector. Following the concept of taking the projector as an inverse camera, we retrieve the image conic of the sphere on the projector plane based on a pole-polar relationship we found. At least 3 image conics on the image plane of each device are required to calculate the intrinsic parameters of the device. The extrinsic parameters for all devices in the system are determined by the position of sphere centers in each coordinates frame of the device. Based on the isotropy of the calibration object (sphere), this work is mainly interested in accomplishing the entire calibration for multiple camera-projector systems in which sensors surround a central observation volume. Experiments are conducted on both synthetic and real datasets to evaluate its performance.

Three-dimensional face recognition has shown its potential to obtain higher recognition accuracy than 2D methods. Among numerous face recognition methods, registration of two faces is comparatively intuitive. We propose a rigid registration method using surface resampling and denoising, which lowers the impact on registration residuals caused by sampling difference and noise, significantly improving the accuracy. While sparsity-inducing norms reduce sensitivity to outliers and missing data, with preprocessing and region segmentation methods, our registration method is applied to face verification. Without data-driven learning or training, only residuals of rigid registration are utilized, and verification rates at 0.1% FAR are as follows: 100% for n versus n, 96.9% for n versus all, and 98.6% for ROC III experiment on FRGC v2.0 database, and 100% for n versus n and 95.7% for n versus all on Bosphorus database. Experiments show that the proposed algorithm outperforms the state-of-the-art algorithms and is preferable in a verification scenario.

The effectiveness of the renowned empirical mode decomposition (EMD) is affected by the mode-mixing problem (MMP) if a signal contains intermittent modes. The ensemble EMD (EEMD) and several modified and extended algorithms solve this problem by adding random white noises. However, the necessary large size of the ensemble and the inevitable manual intervention limits the application of EEMD. In this letter, a novel regenerated phase-shifted sinusoid-assisted EMD (RPSEMD) is proposed. Sinusoids with different scales are iteratively generated and added to cope with all possible MMPs in different intrinsic modes (IMs), where each sinusoid is designed adaptively and automatically. Furthermore, the sinusoids are shifted for better retaining the details of each IM and eliminating the added sinusoids. In the comparison experiments, the RPSEMD provides more reasonable results with less computation time.

A 3D face recognition method using region-based extended local binary pattern (eLBP) is proposed. First, the depth image converted from the preprocessed 3D pointclouds is normalized. Then, different regions according to their distortions under facial expressions are extracted by binary masks and represented by the uniform pattern of extended LBP. Finally, sparse representation classifier (SRC) is adopted for classification on the single region. Feature-level and score-level fusion with weight-sparse representation classifier (W-SRC) are also tested and compared, and the latter has better performance. The experiments on FRGC v2.0 database demonstrate that the proposed method is robust and efficient.

In this paper, the importance of cost aggregation for belief propagation (BP) and the interaction of them are discussed. A global stereo matching algorithm based on BP with local edge detection-based cost aggregation is proposed. Firstly, a virtual closed edge is formed surrounding each pixel via second derivative operator in order to construct the adaptive window. Then, for centered pixel, local cost aggregation is calculated on support pixels in adaptive window. Finally, BP optimization algorithm is used to obtain the disparity. The experiments based on Middlebury benchmark indicate that local edge detection-based cost aggregation can do well with BP and also show encouraging results of proposed stereo matching algorithm.

Achieving high accuracy in the presence of expression variation remains one of the most challenging aspects of 3D face recognition. In this paper, we propose a novel recognition approach for robust and efficient matching. The framework is based on shape processing filters that divide face into three components according to its frequency spectral. Low-frequency band mainly corresponds to expression changes. High-frequency band represents noise. Mid-frequency band is selected for expression-invariant feature which contains most of the discriminative personal-specific deformation information. By using shape filter, it offers a dramatic performance improvement for both accuracy and robustness. We conduct extensive experiments on FRGC v2 databases to verify the efficacy of the proposed algorithm, and validate the above claims.

3D face recognition is complicated by the presence of expression variation. In this paper, we present an automatic 3D face recognition method which can differentiate the expression deformations from the interpersonal differences and recognize faces with expressions being removed. The deformations caused by expression and interpersonal difference are firstly learnt from training set, respectively. Then the deformations are linearly combined to synthesize new face with certain expression. When a target face comes in, the synthesized face is used to match it by adjusting the coefficients in the linear combination. After the matching process, coefficients corresponding to the interpersonal differences are chosen as features for recognition. We perform experiments on the FRGC v2.0 database and good performance is obtained.

A new type controller, fuzzy neural networks sliding mode controller (FNNSMC), is developed for a class of large-scale systems with unknown bounds of high-order interconnections and disturbances. Although sliding mode control is simple and insensitive to uncertainties and disturbances, there are two main problems in the sliding mode controller (SMC): control input chattering and the assumption of known bounds of uncertainties and disturbances. The FNNSMC, which incorporates the fuzzy neural networks (FNNs) and the SMC, can eliminate the chattering by using the continuous output of the FNN to replace the "discontinuous" sign term in the SMC. The bounds of uncertainties and disturbances are also not required in the FNNSMC design. Two examples are presented to support the validity of the new controller. The simulation results show that the FNNSMC is robuster than the SMC.