Heredia Conde, Miguel
4 results
Now showing 1 - 4 of 4
- Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Kalman Filter-Driven Blind Source Localization for Passive 3D ToF Imaging(2023); ; Passive 3D Time-of-Flight (ToF) imaging faces a significant challenge in accurate depth recovery, where the source position is unavailable. In this letter, we present a probabilistic approach based on the Kalman filter which keeps track of source location, thus, avoiding the need for an initial guess to jointly determine the 3D source position and correct depth information. The proposed approach is able to reach a source location error of 0.8 cm by exploiting pseudo-measurements of the plane fitting constraint acquired by a passive ToF camera which exploits a bistatic algorithm with a gradient descent method. Computer experiments are carried out to demonstrate the robustness of the proposed method in realistic scenarios where no initial guess is available. The results show the feasibility of blind source localization with mm accuracy. This contributes to widening the applicability of passive 3D imaging in a number of application fields, such as autonomous driving, and robot navigation.Source Type:Article4 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Performance Evaluation of State-of-the-Art High-Resolution Time-of-Flight CamerasIt has been about 20 years since the disruptive appearance of the first Time-of-Flight (ToF) cameras. Since then, ToF imaging has progressively evolved. Nowadays, ToF sensors have broken the barrier of the 1 MPix resolution and a significant number of high-resolution ToF cameras has appeared in the market. In order to provide a better understanding of their performance and applications, we experimentally evaluate three state-of-the-art high-resolution ToF cameras such as Azure Kinect, Helios2, and S100D, together with the solid-state LiDAR L515. We perform various experiments to examine some key parameters, such as warm-up times, accuracy, precision, lateral and axial resolutions, edge noise, unsteady scenes, and modulated waveform and optical power. Our evaluation draws various conclusions: S100D shows fluctuations within 1 mm after being powered up while the others require warm-up times. Azure Kinect, Helios2, and L515 can achieve precision within 2 mm in a measuring range of 0.5 m to 3 m. Helios2 and S100D are more severely affected by dynamic scenes. Finally, the point clouds generated for a white panel at a distance of 1.5 m show that flying pixels are present in all cameras, being this problem less acute for the L515.Source Type:Article5 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Query by Example in Remote Sensing Image Archive Using Enhanced Deep Support Vector Data DescriptionThis Article studies remote sensing image retrieval using kernel-based support vector data description (SVDD). We exploit deep SVDD, which is a well-known method for one-class classification to recover the most relevant samples from the archive. To this end, a deep neural network (DNN) is jointly trained to map the data into a hypersphere of minimum volume in the latent space. It is expected that similar samples to the query are compressed inside of the hypersphere. The closest embedding to the center of the hypersphere is related to the most relevant sample to query. We enhance deep SVDD by injecting the statistical information of data to the DNN by means of additional terms in the cost function. The first enhancement method takes advantage of covariance regularization of batches of the training set to penalize unnecessary redundancy and minimize the correlation between the different dimensions of the embedding. The second method involves unlocking the hypersphere's predefined center while preventing network divergence during training. Therefore, two parameters are designed to control the importance of the drifting of the center and the importance of a fixed predefined center (convergence), respectively. This has been implemented by considering the average of batches of embedding in each iteration as the updated center. This pushes irrelevant samples away from query samples, making data clustering easier for the DNN. The performance of the proposed methods is evaluated on benchmark datasets.Source Type:Article1 - Some of the metrics are blocked by yourconsent settings
Publication Access status: Metadata only , Sparsity-Aware 3-D ToF Sensing<p>In this work, we propose several time-of-flight (ToF) sensing schemes which tackle the challenge of covering very-wide areas and long ranges in nearly real time, with relatively simple implementation and low associated computational load. We thoroughly describe two methodologies for the resolution of the inverse problem. First, we extend a greedy algorithm, such as orthogonal matching pursuit (OMP), by considering an initial refinement of the spatial domain in which the signal recovery is performed. Then, we propose various nonadaptive techniques for the construction of the sensing matrices, relying on the optimization of coherence and density. We further develop them by including an additional verification step which accounts for the non-instantaneous transitions from one element to another of the code and avoids any possible coincidence between rising and falling edges which may degrade the coherence. We also investigate the upper super-resolution limit, the over-sampling rate which yields unitary coherence, by considering the instrument response function (IRF) of the ToF sensor. Second, we expand an adaptive sensing scheme in which the rows of the sensing matrix are generated accounting for the information from previous measurements, such as adaptive progressive edge growth algorithm(APEG), by considering several groups of signals during the adaptation of the sensing matrices. The signals are then individually recovered for each pixel via OMP over the identified joint signal support. We validate the proposed methodologies by numerical simulations over datasets from stereo and ToF cameras.</p>Source Type:Article2
