Live demonstration: On the distance estimation of moving targets with a Stereo-Vision AER system

Domínguez-Morales, Manuel; Jiménez-Fernández, Ángel; Paz-Vicente, R.; Jiménez, G.; Linares-Barranco, A.

doi:10.1109/iscas.2012.6272137

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A VGA-sized DVS would generate about 18 times more data than the 128 × 128 sensor used for this paper if the objects filled a proportionally larger number of pixels, but even then the processing of the estimated 400 keps from the sensor would barely load a present-day's microprocessor CPU load and would be within the capabilities of modestly-powered embedded processors. As demonstrated by this work and other implementations (Linares-Barranco et al, 2007; Conradt et al, 2009a; Domínguez-Morales et al, 2012; Ni et al, 2013), the use of event-driven sensors can enable faster and lower-power robots of the future.…”

Section: Resultsmentioning

confidence: 61%

“…Other related work that has integrated an event-based neuromorphic vision sensor in a robot includes CAVIAR, a completely spike-hardware based visual tracking system (Serrano-Gotarredona et al, 2009), a pencil balancing robot using a pair of embedded-processor DVS cameras (Conradt et al, 2009a), which was first prototyped using two DVS cameras interfaced by USB (Conradt et al, 2009b), a demonstration of real-time stereo distance estimation computed on an FPGA with 2 DVS cameras (Domínguez-Morales et al, 2012), an embedded FPGA-based visual feedback system using a DVS (Linares-Barranco et al, 2007), and a micro gripper haptic feedback system (Ni et al, 2013) which uses a DVS as one of the two input sensors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

2013

View full text Add to dashboard Cite

Conventional vision-based robotic systems that must operate quickly require high video frame rates and consequently high computational costs. Visual response latencies are lower-bound by the frame period, e.g., 20 ms for 50 Hz frame rate. This paper shows how an asynchronous neuromorphic dynamic vision sensor (DVS) silicon retina is used to build a fast self-calibrating robotic goalie, which offers high update rates and low latency at low CPU load. Independent and asynchronous per pixel illumination change events from the DVS signify moving objects and are used in software to track multiple balls. Motor actions to block the most “threatening” ball are based on measured ball positions and velocities. The goalie also sees its single-axis goalie arm and calibrates the motor output map during idle periods so that it can plan open-loop arm movements to desired visual locations. Blocking capability is about 80% for balls shot from 1 m from the goal even with the fastest-shots, and approaches 100% accuracy when the ball does not beat the limits of the servo motor to move the arm to the necessary position in time. Running with standard USB buses under a standard preemptive multitasking operating system (Windows), the goalie robot achieves median update rates of 550 Hz, with latencies of 2.2 ± 2 ms from ball movement to motor command at a peak CPU load of less than 4%. Practical observations and measurements of USB device latency are provided1.

show abstract

Section: Resultsmentioning

confidence: 61%

Section: Introductionmentioning

confidence: 99%

Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

2013

View full text Add to dashboard Cite

show abstract

“…In 2012 two projects were completed, VULCANO (ultra-fast frame-less vision by events. Application to automotion and anthropomorphic cognitive robotics) [198] which was begun in 2010, and SAMANTA I and II (Multi-chip address-eventrepresentation Vision system for robotics platform I & II) [199] which was begun in 2003. Currently, the group is working on the BIOSENSE project (Bioinspired event-based system for sensory fusion and neurocortical processing) [200] which aims to create a robotic platform based on modular AER technology.…”

Section: Other Projectsmentioning

confidence: 99%

Parallel Computing for Brain Simulation

Pastur-Romay

Porto-Pazos

Cedrón

2017

CTMC

View full text Add to dashboard Cite

This paper presents an up-to-date review about the main research projects that are trying to simulate and/or emulate the human brain. They employ different types of computational models using parallel computing: digital models, analog models and hybrid models. This review includes the current applications of these works, as well as future trends. It is focused on various works that look for advanced progress in Neuroscience and still others which seek new discoveries in Computer Science (neuromorphic hardware, machine learning techniques). Their most outstanding characteristics are summarized and the latest advances and future plans are presented. In addition, this review points out the importance of considering not only neurons: Computational models of the brain should also include glial cells, given the proven importance of astrocytes in information processing.

show abstract

“…The circuit can be also designed to achieve the efficiency of low power consumption by combining an active continuous-time front-end logarithmic photoreceptor [ 10 ]. In the algorithm methods, the visual information (such as an image) can be calculated by the address-event-representation [ 11 ] or by constructing stereo vision with cameras [ 12 ]. However, the devices for matching are more expensive than consumer cameras.…”

Section: Introductionmentioning

confidence: 99%

Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection

Liaw

Huang

et al. 2020

Sensors

View full text Add to dashboard Cite

One of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is the well-known census transform, which has the problem of conversion window selection. In this paper, three methods are proposed to improve the performance of the census transform. The first one uses a low-pass band of the wavelet to reduce the computation loading and a high-pass band of the wavelet to modify the disparity. The main idea of the second method is the adaptive size selection of the conversion window by edge information. The third proposed method is to apply the adaptive window size to the previous sparse census transform. In the experiments, two indexes, percentage of bad matching pixels (PoBMP) and root mean squared (RMS), are used to evaluate the performance with the known ground truth data. According to the results, the computation required can be reduced by the multiresolution feature of the wavelet transform. The accuracy is also improved with the modified disparity processing. Compared with previous methods, the number of operation points is reduced by the proposed adaptive window size method.

show abstract

Live demonstration: On the distance estimation of moving targets with a Stereo-Vision AER system

Cited by 8 publications

References 13 publications

Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

Parallel Computing for Brain Simulation

Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection

Contact Info

Product

Resources

About