Julián Caba

Dr. Julián Caba

Unersidad de Castilla-La Mancha
+1
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 November 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Julián CabaJulián Caba
Julián Caba
MDMaría Díaz
María Díaz
Jesús BarbaJesús Barba
Jesús Barba
RGRaul Guerra
Raul Guerra
JHJosé Antonio de la Torre las Heras
José Antonio de la Torre las Heras
Remote-sensing platforms, such as Unmanned Aerial Vehicles, are characterized by limited power budget and low-bandwidth downlinks. Therefore, handling hyperspectral data in this context can jeopardize the operational time of the system. FPGAs have been traditionally regarded as the most power-efficient computing platforms. However, there is little experimental evidence to support this claim, which is especially critical since the actual behavior of the solutions based on reconfigurable technology is highly dependent on the type of application. In this work, a highly optimized implementation of an FPGA accelerator of the novel HyperLCA algorithm has been developed and thoughtfully analyzed in terms of performance and power efficiency. In this regard, a modification of the aforementioned lossy compression solution has also been proposed to be efficiently executed into FPGA devices using fixed-point arithmetic. Single and multi-core versions of the reconfigurable computing platforms are compared with three GPU-based implementations of the algorithm on as many NVIDIA computing boards: Jetson Nano, Jetson TX2 and Jetson Xavier NX. Results show that the single-core version of our FPGA-based solution fulfils the real-time requirements of a real-life hyperspectral application using a mid-range Xilinx Zynq-7000 SoC chip (XC7Z020-CLG484). Performance levels of the custom hardware accelerator are above the figures obtained by the Jetson Nano and TX2 boards, and power efficiency is higher for smaller sizes of the image block to be processed. To close the performance gap between our proposal and the Jetson Xavier NX, a multi-core version is proposed. The results demonstrate that a solution based on the use of various instances of the FPGA hardware compressor core achieves similar levels of performance than the state-of-the-art GPU, with better efficiency in terms of processed frames by watt.

11 March 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
Julián CabaJulián Caba
Julián Caba
MDMaría Díaz
María Díaz
Jesús BarbaJesús Barba
Jesús Barba
RGRaul Guerra
Raul Guerra
SESoledad Escolar
Soledad Escolar
Sebastian LopezSebastian Lopez
Sebastian Lopez
Onboard data processing for on-the-fly decision-making applications has recently gained momentum in the field of remote sensing. In this context, hyperspectral anomaly detection has received a special attention since its main purpose lays on the identification of abnormal events in an unsupervised manner. Nevertheless, onboard real-time hyperspectral image processing still poses several challenges before becoming a reality. This is why there is an emerging trend towards the development of hardware-friendly algorithmic solutions embedded in reconfigurable devices. In this context, this work contributes with a hardware architecture that ensures a progressive line processing in time-sensitive applications limited by the scarcity of hardware resources. In this sense, we have implemented the state-of-the-art HW-LbL-FAD detector on a reconfigurable hardware for a real-time performance. Specifically, we have selected a cost-optimized FPGA (ZC7Z020-CLG484) to implement our solution whose results draw up a good trade-off between the following three features: time performance, energy consumption and cost. The experimental results indicate our hardware component is able to process hyperspectral images of 825x1024 pixels and 160 bands in 0.51 seconds with a power-budget of 1.3 watts and a device cost around 150 C. Regarding detection performance, the HW-LbL-FAD algorithm outperforms other state-of-the-art algorithms.

12 September 2014 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Closed access
TCTeresa G. Cervero
Teresa G. Cervero
Julián CabaJulián Caba
Julián Caba
Sebastian LopezSebastian Lopez
Sebastian Lopez
JGJulio Dondo Gazzano
Julio Dondo Gazzano
RSRoberto Sarmiento
Roberto Sarmiento
Juan Carlos LópezJuan Carlos López
Juan Carlos López
Earth observation hyperspectral imaging instruments capture and collect hundreds of different wavelength data corresponding to the same surface. As a result, tons of information must be stored, processed, and transmitted to ground by means of a combination of time-consuming processes. However, one of the requirements of paramount importance when dealing with applications that demand swift responses is the ability to achieve real-time. In this sense, the authors present a flexible and adaptable Field-Programmable Gate Array (FPGA)-based solution for extracting the endmembers of a hyperspectral image according to the Modified Vertex Component Analysis (MVCA) algorithm. The proposed approach is capable of adapting its parallelization execution by scaling the execution in hardware. Thus, the solution uses the dynamic and partial reconfiguration property of FPGAs in order to exploit and vary the level of parallelism at run-time. In order to validate the convenience of using this kind of solutions, the performance of our proposal has been assessed with a set of synthetic images as well as with the well-known Cuprite hyperspectral image. The achieved results demonstrate that the proposed system might be dynamically scaled without significantly affecting total execution times, being able to extract the endmembers of the Cuprite dataset in real-time.

7 March 2024 in Multimedia Tools and Applications
Verified
Journal Article
Open access
PDF file
JMJosé L. Mira
José L. Mira
Jesús BarbaJesús Barba
Jesús Barba
FCFrancisco P. Romero Chicharro
Francisco P. Romero Chicharro
SESoledad Escolar
Soledad Escolar
Julián CabaJulián Caba
Julián Caba
Juan Carlos LópezJuan Carlos López
Juan Carlos López
The automation of insect pest control activities implies the use of classifiers to monitor the temporal and spatial evolution of the population using computer vision algorithms. In this regard, the popularisation of supervised learning methods represents a breakthrough in this field. However, their claimed effectiveness is reduced regarding working in real-life conditions. In addition, the efficiency of the proposed models is usually measured in terms of their accuracy, without considering the actual context of the sensing platforms deployed at the edge, where image processing must occur. Hence, energy consumption is a key factor in embedded devices powered by renewable energy sources such as solar panels, particularly in energy harvesting platforms, which are increasingly popular in smart farming applications. In this work, we perform a two-fold performance analysis (accuracy and energy efficiency) of three commonly used methods in computer vision (e.g., HOG+SVM, LeNet-5 CNN, and PCA+Random Forest) for object classification, targeting the detection of the olive fly in chromatic traps. The training and testing of the models were carried out using pictures captured in various realistic conditions to obtain more reliable results. We conducted an exhaustive exploration of the solution space for each evaluated method, assessing the impact of the input dataset and configuration parameters on the learning process outcomes. To determine their suitability for deployment on edge embedded systems, we implemented a prototype on a Raspberry Pi 4 and measured the processing time, memory usage, and power consumption. The results show that the PCA-Random Forest method achieves the highest accuracy of 99%, with significantly lower processing time (approximately 6 and 48 times faster) and power consumption (approximately 10 and 44 times lower) compared with its competitors (LeNet-5-based CNN and HOG+SVM).

1 March 2015 in Journal of Systems Architecture
Verified
Journal Article
Closed access
Jesús BarbaJesús Barba
Jesús Barba
MSMaría José Santofimia
María José Santofimia
JGJulio Dondo Gazzano
Julio Dondo Gazzano
FRFernando Rincón
Fernando Rincón
Julián CabaJulián Caba
Julián Caba
Juan Carlos LópezJuan Carlos López
Juan Carlos López

30 November 2020 in Electronics
Verified
Journal Article
Open access
PDF file
Julián CabaJulián Caba
Julián Caba
FRFernando Rincón
Fernando Rincón
Jesús BarbaJesús Barba
Jesús Barba
JHJosé Antonio de la Torre las Heras
José Antonio de la Torre las Heras
Juan Carlos LópezJuan Carlos López
Juan Carlos López
High-Level Synthesis (HLS) tools provide facilities for the development of specialized hardware accelerators (HWacc). However, the verification stage is still the longest phase in the development life-cycle. Unlike in the software industry, HLS tools lack testing frameworks that could cover the whole design flow, especially the on-board verification stage of the generated RTL. This work introduces a framework for on-board verification of HLS-based modules by using reconfigurable systems and Docker containers with the aim to automate the verification process and preserve a clean testing environment, making the testbed reusable across different stages of the design flow. Moreover, our solution features a mechanism to check timing requirements of the HWacc. We have applied our solution to the C-kernels of the CHStone Benchmark on a Zedboard, in which the on-board verification process has been accelerated up to four times.