In the facial expression recognition task, a good-performing convolutional neural network (CNN) model trained on one dataset (source dataset) usually performs poorly on another dataset (target dataset). This is because the feature distribution of the same emotion varies in different datasets. To improve the cross-dataset accuracy of the CNN model, we introduce an unsupervised domain adaptation method, which is especially suitable for unlabelled small target dataset. In order to solve the problem of lack of samples from the target dataset, we train a generative adversarial network (GAN) on the target dataset and use the GAN generated samples to fine-tune the model pretrained on the source dataset. In the process of fine-tuning, we give the unlabelled GAN generated samples distributed pseudolabels dynamically according to the current prediction probabilities. Our method can be easily applied to any existing convolutional neural networks (CNN). We demonstrate the effectiveness of our method on four facial expression recognition datasets with two CNN structures and obtain inspiring results.

Three-dimensional (3D) reconstruction using line structured light vision system commonly cooperates with motion restraint devices, such as parallel guide rail push-broom devices. In this study, we propose a visual positioning method to eliminate the motion constraint. An extended orthogonal iteration algorithm for visual positioning is proposed to obtain the precise position of the line structured light binocular camera system during movement. The algorithm uses the information acquired by the binocular camera, and produces a better positioning accuracy than the traditional vision localization algorithm. Furthermore, a global optimization method is proposed to calculate the poses of the camera relative to the world coordinate system at each shooting position. This algorithm effectively reduces the error accumulation and pose drift during visual positioning, and 3D information of the surface can be measured via the proposed free-moving line structured light vision system. The simulation and physical experiments performed herein validate the proposed method and demonstrate the significant improvement in the reconstruction accuracy: when the test distance is 1.5 m, the root mean square error of the point cloud is within 0.5 mm.

Multi-camera systems are widely used in the fields of airborne remote sensing and unmanned aerial vehicle imaging. The measurement precision of these systems depends on the accuracy of the extrinsic parameters. Therefore, it is important to accurately calibrate the extrinsic parameters between the onboard cameras. Unlike conventional multi-camera calibration methods with a common field of view (FOV), multi-camera calibration without overlapping FOVs has certain difficulties. In this paper, we propose a calibration method for a multi-camera system without common FOVs, which is used on aero photogrammetry. First, the extrinsic parameters of any two cameras in a multi-camera system is calibrated, and the extrinsic matrix is optimized by the re-projection error. Then, the extrinsic parameters of each camera are unified to the system reference coordinate system by using the global optimization method. A simulation experiment and a physical verification experiment are designed for the theoretical arithmetic. The experimental results show that this method is operable. The rotation error angle of the camera’s extrinsic parameters is less than 0.001rad and the translation error is less than 0.08 mm.

Aligning and balancing the marginal and conditional feature distributions are two critical procedures for unsupervised domain adaptation (UDA) problems. However, existing methods usually consider the former while ignoring the latter. To improve the problems of instability and imbalance, we propose the Adaptative Joint Distribution Adaptation Network (AJDAN) by analyzing the multi-modal interactions between the two types of distributions and adding a self-learning network to simultaneously balance them. Furthermore, we give higher weights to samples that are far away from the domain boundary (easy-to-classify samples) using Strong Binary Cross-Entropy (SBCE). The strong alignment strategy is adjustable and allows the network to better train easy-to-classify samples than traditional Binary Cross-Entropy (BCE) in various scenarios. The experiment shows that AJDAN with SBCE (AJDAN+S) provides an average of 68.3% accuracy on the Office-Home dataset, and 89.1% accuracy on the Office31 dataset, showing its superiority by 2~3 percent above the existing state-of-the-art methods.

This paper addresses the problem of relative pose estimation for multiple cameras in the context of motion-based camera calibration. Relative pose is found from a set of camera–target relative poses. A least-square kind loss function is established using 3D relative Riemannian metrics of targets and cameras. Lie algebra-based solvers are proposed for orientation and pose estimation. Multiple cameras are calibrated without common targets or features in space using our proposed framework. The simulation and real data evaluation demonstrate that our proposed algorithms can achieve high accuracy with limited and precise camera–target poses.