In this paper, we explore the process of emotional state transition. And the process is impacted by emotional state of interaction objects. First of all, the cognitive reasoning process and the micro-expressions recognition is the basis of affective computing adjustment process. Secondly, the threshold function and attenuation function are proposed to quantify the emotional changes. In the actual environment, the emotional state of the robot and external stimulus are also quantified as the transferring probability. Finally, the Gaussian cloud distribution is introduced to the Gross model to calculate the emotional transitional probabilities. The experimental results show that the model in human–computer interaction can effectively regulate the emotional states, and can significantly improve the humanoid and intelligent ability of the robot. This model is consistent with experimental and emulational significance of the psychology, and allows the robot to get rid of the mechanical emotional transfer process.
Fourier transform profilometry (FTP) is a classic three-dimensional (3D) shape measurement technique that can retrieve the wrapped phase from a single fringe pattern. However, suffering from the spectral leakage and overlapping problems, it generally yields a coarse phase map with low spatial resolution and precision. Recently, deep learning has been introduced to the field of Fringe projection profilometry (FPP), revealing promising results in fringe analysis, phase unwrapping, depth constraint and system calibration. However, for absolute shape measurement of general objects, the inherent depth ambiguity problem of a single fringe is still insurmountable. In this work, we propose a composite deep learning framework for absolute 3D shape measurement based on single fringe phase retrieval and speckle correlation. Our method combines the advantages of FPP techniques for high-resolution phase retrieval and speckle correlation approaches for robust unambiguous depth measurement. The proposed deep learning framework comprises two paths: one is a U-net-structured network, which is used to extract the wrapped phase maps from a single fringe pattern with high accuracy (but with depth ambiguities). The other stereo matching network produces the initial absolute (but with low resolution) disparity map from an additional speckle pattern. The initial disparity map is refined by exploiting the wrapped phase maps as an additional constraint and finally, a high-accuracy high-resolution disparity map for absolute 3D measurement can be obtained. Experimental results demonstrated that the proposed deep-learning-based method could realize high-precision absolute 3D measurement with an accuracy of 50 µm for measuring objects with complex surfaces.
Sparse coding performs well in image classification. However, robust target recognition requires a lot of comprehensive template images and the sparse learning process is complex. We incorporate sparsity into a template matching concept to construct a local sparse structure matching (LSSM) model for general infrared target recognition. A local structure preserving sparse coding (LSPSc) formulation is proposed to simultaneously preserve the local sparse and structural information of objects. By adding a spatial local structure constraint into the classical sparse coding algorithm, LSPSc can improve the stability of sparse representation for targets and inhibit background interference in infrared images. Furthermore, a kernel LSPSc (K-LSPSc) formulation is proposed, which extends LSPSc to the kernel space to weaken the influence of the linear structure constraint in nonlinear natural data. Because of the anti-interference and fault-tolerant capabilities, both LSPSc- and K-LSPSc-based LSSM can implement target identification based on a simple template set, which just needs several images containing enough local sparse structures to learn a sufficient sparse structure dictionary of a target class. Specifically, this LSSM approach has stable performance in the target detection with scene, shape and occlusions variations. High performance is demonstrated on several datasets, indicating robust infrared target recognition in diverse environments and imaging conditions.
In binocular stereo matching, mistakes are relatively easy to appear in low-texture region due to the weak detail information. In order to eliminate the matching ambiguity as well as guarantee the matching rate, this paper proposes a stereo matching algorithm based on image segmentation. In most low-texture region, traditional cost functions are usually used, and the algorithm can only ameliorated through methods such as reasonable support window, dynamic programming and so on. The results of these algorithms make the whole image smooth, and lose many details. The matching cost function in our algorithm is based on the assumption that pixels are similar in homogeneous area, and reduce the use of multiplication so as to obtain better visual effects and decrease the computational complexity. The first is forming the segmentation maps of stereoscopic images as the guidance. Next comes calculating the aggregation cost in stereo matching in both horizontal and vertical direction successively referring to the segmentation maps. Eventually achieving the final disparity map with optimization algorithm, using WTA(Winner-Takes-All) as principle. The computational complexity of this algorithm is independent of the window size, and suitable for different sizes and shapes. The results of experimental show that this algorithm can get better matching precision about the colorful low-texture stereo image pairs, with few increase in computational complexity. This algorithm, to some extent, can improve the match quality of the regions with repeat texture.
The scattering of light after passing through a complex medium poses challenges in many fields. Any point in the collected speckle will contain information from the entire target plane because of the randomness of scattering. The detailed information of complex targets is submerged in the aliased signal caused by random scattering, and the aliased signal causes the quality of the recovered target to be degraded. In this paper, a new neural network named Adaptive Encoding Scattering Imaging ConvNet (AESINet) is constructed by analyzing the physical prior of speckle image redundancy to recover complex targets hidden behind the opaque medium. AESINet reduces the redundancy of speckle through adaptive encoding which effectively improves the separability of data; the encoded speckle makes it easier for the network to extract features, and helps restore the detailed information of the target. The necessity for adaptive encoding is analyzed, and the ability of this method to reconstruct complex targets is tested. The peak signal-to-noise ratio (PSNR) of the reconstructed target after adaptive encoding can be improved by 1.8 dB. This paper provides an effective reference for neural networks combined with other physical priors in scattering processes.
Fringe projection profilometry (i.e., FPP) has been one of the most popular 3-D measurement techniques. The phase error due to system random noise becomes non-ignorable when fringes captured by a camera have a low fringe modulation, which are inevitable for objects’ surface with un-uniform reflectivity. The phase calculated from these low-modulation fringes may have a non-ignorable phase error and generate 3-D measurement error. Traditional methods reduce the phase error with losing details of 3-D shapes or sacrificing the measurement speed. In this paper, a deep learning-based fringe modulation-enhancing method (i.e., FMEM) is proposed, that transforms two low-modulation fringes with different phase shifts into a set of three phase-shifted high-modulation fringes. FMEM enables to calculate the desired phase from the transformed set of high-modulation fringes, and result in accurate 3-D FPP without sacrificing the speed. Experimental analysis verifies its effectiveness and accurateness.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)