Monocular cues are one of the key elements considered by humans to appreciate the depth in their environment, even using only one eye. The idea of this paper is to help a deep neural network to perform the task of monocular depth estimation by integrating the so-called monocular cues into the learning process. To this end, we first propose an ontology model to define several human knowledge, mainly contextual, semantic, and geometric. Thus, thanks to ontology rules that imitate human-like reasoning, monocular cues maps are extracted and integrated into the deep neural network. The proposed approach can be applied in several domains, mainly autonomous driving, either in the urban environment or the industrial one. Our method was validated on the urban driving CityScapes dataset and have shown promising results.

In this paper, we study the problem of autonomous and reliable positioning of a camera w.r.t. an object when only this latter is known but not the rest of the scene. We propose to combine the advantages and efficiency of a visual servoing scheme and the generalization ability of a generative adversarial network. The paper describes how to efficiently create a synthetic dataset in order to train a network that predicts an intermediate visual keyframe between two images. Subsequent predictions are used as visual features to autonomously converge towards the desired pose even for large displacements. We show that the proposed method can be used without any prior knowledge on the scene appearance except for the object itself, while being robust to various lighting conditions and specular surfaces. We provide experimental results, both in simulation and using a real service robot platform to validate and evaluate the effectiveness, robustness, and accuracy of our approach.

The direct use of the entire photometric image information as dense features for visual servoing brings several advantages. First, it does not require any feature detection, matching, or tracking process. Thanks to the redundancy of visual information, the precision at convergence is highly accurate. However, the corresponding highly nonlinear cost function reduces the convergence domain. In this paper, we propose visual servoing based on the analytical formulation of Gaussian mixtures to enlarge the convergence domain. Pixels are represented by two-dimensional Gaussian functions that denote a “power of attraction.” In addition to the control of the camera velocities during the servoing, we also optimize the Gaussian spreads allowing the camera to precisely converge to a desired pose even from a far initial one. Simulations show that our approach outperforms the state of the art and real experiments show the effectiveness, robustness, and accuracy of our approach.

Many fields of application could benefit from an accurate registration of measurements of different modalities over a known 3D model. However, aligning a 2D image to a 3D model is a challenging task and is even more complex when the two have a different modality. Most of the 2D/3D registration methods are based on either geometric or dense visual features. Both have their own advantages and their own drawbacks. We propose, in this paper, to mutually exploit the advantages of one feature type to reduce the drawbacks of the other one. For this, an hybrid registration framework has been designed to mutually align geometrical and dense visual features in order to obtain an accurate final 2D/3D alignment. We evaluate and compare the proposed registration method on real data acquired by a robot equipped with several visual sensors. The results highlights the robustness of the method and its ability to produce wide convergence domain and a high registration accuracy.

The advantages of using the entire photometric image information as visual feature are: it does not require any feature detections, matching or tracking process. To enlarge the convergence domain, we propose to accomplish visual servoing based on the analytical formulation of Gaussian mixtures to model the images. During the servoing, we consider the optimization of the Gaussian spreads allowing the camera to converge to a desired pose even from a far initial one. Simulation that overcomes the state-of-the-art and real experiments highlight the success of our approach.