![]() ; Aouada, Djamila ![]() in ACM Transactions on Multimedia Computing, Communications, & Applications (2018) Detailed reference viewed: 269 (11 UL)![]() ; Aouada, Djamila ![]() in IEEE Transactions on Pattern Analysis and Machine Intelligence (2016), 39(10), 2045-2059 We propose a novel approach for enhancing depth videos containing non-rigidly deforming objects. Depth sensors are capable of capturing depth maps in real-time but suffer from high noise levels and low ... [more ▼] We propose a novel approach for enhancing depth videos containing non-rigidly deforming objects. Depth sensors are capable of capturing depth maps in real-time but suffer from high noise levels and low spatial resolutions. While solutions for reconstructing 3D details in static scenes, or scenes with rigid global motions have been recently proposed, handling unconstrained non-rigid deformations in relative complex scenes remains a challenge. Our solution consists in a recursive dynamic multi-frame superresolution algorithm where the relative local 3D motions between consecutive frames are directly accounted for. We rely on the assumption that these 3D motions can be decoupled into lateral motions and radial displacements. This allows to perform a simple local per-pixel tracking where both depth measurements and deformations are dynamically optimized. The geometric smoothness is subsequently added using a multi-level L1 minimization with a bilateral total variation regularization. The performance of this method is thoroughly evaluated on both real and synthetic data. As compared to alternative approaches, the results show a clear improvement in reconstruction accuracy and in robustness to noise, to relative large non-rigid deformations, and to topological changes. Moreover, the proposed approach, implemented on a CPU, is shown to be computationally efficient and working in real-time. [less ▲] Detailed reference viewed: 328 (15 UL)![]() ; Aouada, Djamila ![]() in Computer Vision and Image Understanding (2016) Multi-frame super-resolution is the process of recovering a high resolution image or video from a set of captured low resolution images. Super-resolution approaches have been largely explored in 2-D ... [more ▼] Multi-frame super-resolution is the process of recovering a high resolution image or video from a set of captured low resolution images. Super-resolution approaches have been largely explored in 2-D imaging. However, their extension to depth videos is not straightforward due to the textureless nature of depth data, and to their high frequency contents coupled with fast motion artifacts. Recently, few attempts have been introduced where only the super-resolution of static depth scenes has been addressed. In this work, we propose to enhance the resolution of dynamic depth videos with non-rigidly moving objects. The proposed approach is based on a new data model that uses densely upsampled, and cumulatively registered versions of the observed low resolution depth frames. We show the impact of upsampling in increasing the sub-pixel accuracy and reducing the rounding error of the motion vectors. Furthermore, with the proposed cumulative motion estimation, a high registration accuracy is achieved between non-successive upsampled frames with relative large motions. A statistical performance analysis is derived in terms of mean square error explaining the effect of the number of observed frames and the effect of the super-resolution factor at a given noise level. We evaluate the accuracy of the proposed algorithm theoretically and experimentally as function of the SR factor, and the level of contaminations with noise. Experimental results on both real and synthetic data show the effectiveness of the proposed algorithm on dynamic depth videos as compared to state-of-art methods. [less ▲] Detailed reference viewed: 300 (21 UL)![]() Garcia Becerro, Frederic ![]() ![]() in Image and Vision Computing (2015), 41 Detailed reference viewed: 205 (3 UL)![]() Al Ismaeil, Kassem ![]() ![]() in IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'15), (Best paper award) (2015, June 12) This paper proposes to enhance low resolution dynamic depth videos containing freely non–rigidly moving objects with a new dynamic multi–frame super–resolution algorithm. Existent methods are either ... [more ▼] This paper proposes to enhance low resolution dynamic depth videos containing freely non–rigidly moving objects with a new dynamic multi–frame super–resolution algorithm. Existent methods are either limited to rigid objects, or restricted to global lateral motions discarding radial displacements. We address these shortcomings by accounting for non–rigid displacements in 3D. In addition to 2D optical flow, we estimate the depth displacement, and simultaneously correct the depth measurement by Kalman filtering. This concept is incorporated efficiently in a multi–frame super–resolution framework. It is formulated in a recursive manner that ensures an efficient deployment in real–time. Results show the overall improved performance of the proposed method as compared to alternative approaches, and specifically in handling relatively large 3D motions. Test examples range from a full moving human body to a highly dynamic facial video with varying expressions. [less ▲] Detailed reference viewed: 266 (21 UL)![]() Afzal, Hassan ![]() ![]() in 16th International Conference on Computer Analysis of Images and Patterns (2015) In this paper, we target enhanced 3D reconstruction of non-rigidly deforming objects based on a view-independent surface representation with an automated recursive filtering scheme. This work improves ... [more ▼] In this paper, we target enhanced 3D reconstruction of non-rigidly deforming objects based on a view-independent surface representation with an automated recursive filtering scheme. This work improves upon the KinectDeform algorithm which we recently proposed. KinectDeform uses an implicit viewdependent volumetric truncated signed distance function (TSDF) based surface representation. The view-dependence makes its pipeline complex by requiring surface prediction and extraction steps based on camera’s field of view. This paper proposes to use an explicit projection-based Moving Least Squares (MLS) surface representation from point-sets. Moreover, the empirical weighted filtering scheme in KinectDeform is replaced by an automated fusion scheme based on a Kalman filter. We analyze the performance of the proposed algorithm both qualitatively and quantitatively and show that it is able to produce enhanced and feature preserving 3D reconstructions. [less ▲] Detailed reference viewed: 375 (34 UL)![]() Afzal, Hassan ![]() ![]() in 22nd International Conference on Pattern Recognition (ICPR'14) (2014) One of the most crucial requirements for building a multi-view system is the estimation of relative poses of all cameras. An approach tailored for a RGB-D cameras based multi-view system is missing. We ... [more ▼] One of the most crucial requirements for building a multi-view system is the estimation of relative poses of all cameras. An approach tailored for a RGB-D cameras based multi-view system is missing. We propose BAICP+ which combines Bundle Adjustment (BA) and Iterative Closest Point (ICP) algorithms to take into account both 2D visual and 3D shape information in one minimization formulation to estimate relative pose parameters of each camera. BAICP+ is generic enough to take different types of visual features into account and can be easily adapted to varying quality of 2D and 3D data. We perform experiments on real and simulated data. Results show that with the right weighting factor BAICP+ has an optimal performance when compared to BA and ICP used independently or sequentially. [less ▲] Detailed reference viewed: 313 (34 UL)![]() Afzal, Hassan ![]() ![]() ![]() in Second International Conference on 3D Vision (2014) In this work we propose KinectDeform, an algorithm which targets enhanced 3D reconstruction of scenes containing non-rigidly deforming objects. It provides an innovation to the existing class of ... [more ▼] In this work we propose KinectDeform, an algorithm which targets enhanced 3D reconstruction of scenes containing non-rigidly deforming objects. It provides an innovation to the existing class of algorithms which either target scenes with rigid objects only or allow for very limited non-rigid deformations or use pre-computed templates to track them. KinectDeform combines a fast non-rigid scene tracking algorithm based on octree data representation and hierarchical voxel associations with a recursive data filtering mechanism. We analyze its performance on both real and simulated data and show improved results in terms of smoothness and feature preserving 3D reconstructions with reduced noise. [less ▲] Detailed reference viewed: 483 (64 UL)![]() Garcia Becerro, Frederic ![]() Patent (2013) Detailed reference viewed: 77 (13 UL)![]() Al Ismaeil, Kassem ![]() ![]() in 20th International Conference on Image Processing (2013, September) We enhance the resolution of depth videos acquired with low resolution time-of-flight cameras. To that end, we propose a new dedicated dynamic super-resolution that is capable to accurately super-resolve a ... [more ▼] We enhance the resolution of depth videos acquired with low resolution time-of-flight cameras. To that end, we propose a new dedicated dynamic super-resolution that is capable to accurately super-resolve a depth sequence containing one or multiple moving objects without strong constraints on their shape or motion, thus clearly outperforming any existing super-resolution techniques that perform poorly on depth data and are either restricted to global motions or not precise because of an implicit estimation of motion. Our proposed approach is based on a new data model that leads to a robust registration of all depth frames after a dense upsampling. The texture-less nature of depth images allows to robustly handle sequences with multiple moving objects as confirmed by our experiments. [less ▲] Detailed reference viewed: 262 (23 UL)![]() Al Ismaeil, Kassem ![]() ![]() in 8th International Symposium on Image and Signal Processing and Analysis (2013) A critical step in multi-frame super-resolution is the registration of frames based on their motion. We improve the performance of current state-of-the-art super-resolution techniques by proposing a more ... [more ▼] A critical step in multi-frame super-resolution is the registration of frames based on their motion. We improve the performance of current state-of-the-art super-resolution techniques by proposing a more robust and accurate registration as early as in the initialization stage of the high resolution estimate. Indeed, we solve the limitations on scale and motion inherent to the classical Shift & Add approach by upsampling the low resolution frames up to the super-resolution factor prior to estimating motion or to median filtering. This is followed by an appropriate selective optimization, leading to an enhanced Shift & Add. Quantitative and qualitative evaluations have been conducted at two levels; the initial estimation and the final optimized super-resolution. Results show that the proposed algorithm outperforms existing state-of-art methods. [less ▲] Detailed reference viewed: 193 (16 UL)![]() Garcia Becerro, Frederic ![]() ![]() in IET Computer Vision (2013), 7(5), 335345 Detailed reference viewed: 321 (23 UL)![]() Al Ismaeil, Kassem ![]() ![]() in Computer Analysis of Images and Patterns, 15th International Conference, CAIP 2013, York, UK, August 27-29, 2013, Proceedings, Part II (2013) Detailed reference viewed: 251 (15 UL)![]() Garcia Becerro, Frederic ![]() ![]() ![]() in Computer Vision – ECCV 2012. Workshops and Demonstrations (2012) Detailed reference viewed: 269 (19 UL)![]() Garcia Becerro, Frederic ![]() ![]() in IEEE Journal of Selected Topics in Signal Processing (2012), 6(5), 1-12 Detailed reference viewed: 239 (6 UL)![]() Garcia Becerro, Frederic ![]() ![]() in 19th IEEE International Conference on Image Processing (2012) Detailed reference viewed: 200 (5 UL)![]() Al Ismaeil, Kassem ![]() ![]() in Pattern Recognition (ICPR), 2012 21st International Conference on (2012) The well-known bilateral filter is used to smooth noisy images while keeping their edges. This filter is commonly used with Gaussian kernel functions without real justification. The choice of the kernel ... [more ▼] The well-known bilateral filter is used to smooth noisy images while keeping their edges. This filter is commonly used with Gaussian kernel functions without real justification. The choice of the kernel functions has a major effect on the filter behavior. We propose to use exponential kernels with L1 distances instead of Gaussian ones. We derive Stein's Unbiased Risk Estimate to find the optimal parameters of the new filter and compare its performance with the conventional one. We show that this new choice of the kernels has a comparable smoothing effect but with sharper edges due to the faster, smoothly decaying kernels. [less ▲] Detailed reference viewed: 158 (11 UL)![]() Garcia Becerro, Frederic ![]() Patent (2011) Detailed reference viewed: 75 (2 UL)![]() Garcia Becerro, Frederic ![]() ![]() in 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance (2011) Detailed reference viewed: 210 (3 UL)![]() Garcia Becerro, Frederic ![]() ![]() in 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA) (2011) Detailed reference viewed: 130 (6 UL) |
||