|
|
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.
|
|
|
|
Jacome-Galarza L.-R., R. R. M. - A., Paillacho Corredores J., Benavides Maldonado J.-L. (2022). Time series in sensor data using state of the art deep learning approaches: A systematic literature review. In VII International Conference on Science, Technology and Innovation for Society (CITIS 2021), mayo 26-28. Smart Innovation, Systems and Technologies. (Vol. 252, pp. 503–514).
Abstract: IoT (Internet of Things) and AI (Artificial Intelligence) are becoming
support tools for several current technological solutions due to significant advancements of these areas. The development of the IoT in various technological fields has contributed to predicting the behavior of various systems such as mechanical, electronic, and control using sensor networks. On the other hand, deep learning architectures have achieved excellent results in complex tasks, where patterns have been extracted in time series. This study has reviewed the most efficient deep learning architectures for forecasting and obtaining trends over time, together with data produced by IoT sensors. In this way, it is proposed to contribute to applications in fields in which IoT is contributing a technological advance such as smart cities, industry 4.0, sustainable agriculture, or robotics. Among the architectures studied in this article related to the process of time series data we have: LSTM (Long Short-Term Memory) for its high precision in prediction and the ability to automatically process input sequences; CNN (Convolutional Neural Networks) mainly in human activity
recognition; hybrid architectures in which there is a convolutional layer for data pre-processing and RNN (Recurrent Neural Networks) for data fusion from different sensors and their subsequent classification; and stacked LSTM Autoencoders that extract the variables from time series in an unsupervised way without the need of manual data pre-processing.Finally, well-known technologies in natural language processing are also used in time series data prediction, such as the attention mechanism and embeddings obtaining promising results.
|
|
|
|
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.
|
|
|
|
Luis Jacome-Galarza, M. V. - C., Miguel Realpe-Robalino, Jose Benavides-Maldonado. (2021). Software Engineering and Distributed Computing in image processing intelligent systems: a systematic literature review. In 19th LACCEI International Multi-Conference for Engineering, Education, and Technology.
Abstract: Deep learning is experiencing an upward technology trend that is revolutionizing intelligent systems in several domains, such as image and speech recognition, machine translation, social network filtering, and the like. By reviewing a total of 80 studies reported from 2016 to 2020, the present article evaluates the application of software engineering to the field
of intelligent image processing systems, it also offers insights about aspects related to distributed computing for this type of systems. Results indicate that several topics of software engineering are mostly applied when academics are involved in developing projects associated to this kind of intelligent systems. The findings provide evidences that Apache Spark is the most
utilized distributed computing framework for image processing. In addition, Tensorflow is a popular framework used to build convolutional neural networks, which are the prevailing deep learning algorithms used in intelligent image processing systems.
Also, among big cloud providers, Amazon Web Services is the preferred computing platform across the industry sectors, followed by Google cloud.
|
|
|
|
Marjorie Chalen, & Boris X. Vintimilla. (2019). Towards Action Prediction Applying Deep Learning. Latin American Conference on Computational Intelligence (LA-CCI); Guayaquil, Ecuador; 11-15 Noviembre 2019, , pp. 1–3.
Abstract: Considering the incremental development future action prediction by video analysis task of computer vision where it is done based upon incomplete action executions. Deep learning is playing an important role in this task framework. Thus, this paper describes recently techniques and pertinent datasets utilized in human action prediction task.
|
|
