2020 |
|
|
Cristhian A. Aguilera, C. A., Cristóbal A. Navarro, & Angel D. Sappa. (2020). Fast CNN Stereo Depth Estimation through Embedded GPU Devices. Sensors 2020, Vol. 2020-June(11), pp. 1–13.
Abstract: Current CNN-based stereo depth estimation models can barely run under real-time
constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art
evaluations usually do not consider model optimization techniques, being that it is unknown what is
the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models
on three different embedded GPU devices, with and without optimization methods, presenting
performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth
estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture
for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically
augmenting the runtime speed of current models. In our experiments, we achieve real-time inference
speed, in the range of 5–32 ms, for 1216 368 input stereo images on the Jetson TX2, Jetson Xavier,
and Jetson Nano embedded devices.
|
|
|
|
Henry O. Velesaca, Raul A. Mira, Patricia L. Suarez, Christian X. Larrea, & Angel D. Sappa. (2020). Deep Learning based Corn Kernel Classification. In The 1st International Workshop and Prize Challenge on Agriculture-Vision: Challenges & Opportunities for Computer Vision in Agriculture on the Conference Computer on Vision and Pattern Recongnition (CVPR 2020) (Vol. 2020-June, pp. 294–302).
Abstract: This paper presents a full pipeline to classify sample sets of corn kernels. The proposed approach follows a segmentation-classification scheme. The image segmentation is performed through a well known deep learning based
approach, the Mask R-CNN architecture, while the classification is performed by means of a novel-lightweight network specially designed for this task—good corn kernel, defective corn kernel and impurity categories are considered.
As a second contribution, a carefully annotated multitouching corn kernel dataset has been generated. This dataset has been used for training the segmentation and
the classification modules. Quantitative evaluations have been performed and comparisons with other approaches provided showing improvements with the proposed pipeline.
|
|
|
|
Henry O. Velesaca, S. A., Patricia L. Suarez, Ángel Sanchez & Angel D. Sappa. (2020). Off-the-Shelf Based System for Urban Environment Video Analytics. In The 27th International Conference on Systems, Signals and Image Processing (IWSSIP 2020) (Vol. 2020-July, pp. 459–464).
Abstract: This paper presents the design and implementation details of a system build-up by using off-the-shelf algorithms for urban video analytics. The system allows the connection to public video surveillance camera networks to obtain the necessary
information to generate statistics from urban scenarios (e.g., amount of vehicles, type of cars, direction, numbers of persons, etc.). The obtained information could be used not only for traffic management but also to estimate the carbon footprint of urban scenarios. As a case study, a university campus is selected to
evaluate the performance of the proposed system. The system is implemented in a modular way so that it is being used as a testbed to evaluate different algorithms. Implementation results are provided showing the validity and utility of the proposed approach.
|
|
|
|
Jorge L. Charco, Angel D. Sappa, Boris X. Vintimilla, & Henry O. Velesaca. (2020). Transfer Learning from Synthetic Data in the Camera Pose Estimation Problem. In The 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020); Valletta, Malta; 27-29 Febrero 2020 (Vol. 4, pp. 498–505).
Abstract: This paper presents a novel Siamese network architecture, as a variant of Resnet-50, to estimate the relative camera pose on multi-view environments. In order to improve the performance of the proposed model
a transfer learning strategy, based on synthetic images obtained from a virtual-world, is considered. The
transfer learning consist of first training the network using pairs of images from the virtual-world scenario
considering different conditions (i.e., weather, illumination, objects, buildings, etc.); then, the learned weight
of the network are transferred to the real case, where images from real-world scenarios are considered. Experimental results and comparisons with the state of the art show both, improvements on the relative pose
estimation accuracy using the proposed model, as well as further improvements when the transfer learning
strategy (synthetic-world data – transfer learning – real-world data) is considered to tackle the limitation on
the training due to the reduced number of pairs of real-images on most of the public data sets.
|
|
