Event Camera Based Real-Time Detection and Tracking of Indoor Ground Robots

Patel, Himanshu; Iaboni, Craig; Lobo, Deepan; Choi, Jiho; Abichandani, Pramod

doi:10.1109/access.2021.3133533

Cited by 20 publications

(16 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It entails using event data to extract features of different types (e.g., corners) and track them through time [ 21 , 22 , 23 ]. As for event-based object detection and tracking, most works have been application-specific, with few similarities overall [ 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ]. We categorize these works as either event-based or combined (i.e., using images and events) approaches.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

High-Temporal-Resolution Object Detection and Tracking Using Images and Events

Shair

Rawashdeh

2022

J. Imaging

View full text Add to dashboard Cite

Event-based vision is an emerging field of computer vision that offers unique properties, such as asynchronous visual output, high temporal resolutions, and dependence on brightness changes, to generate data. These properties can enable robust high-temporal-resolution object detection and tracking when combined with frame-based vision. In this paper, we present a hybrid, high-temporal-resolution object detection and tracking approach that combines learned and classical methods using synchronized images and event data. Off-the-shelf frame-based object detectors are used for initial object detection and classification. Then, event masks, generated per detection, are used to enable inter-frame tracking at varying temporal resolutions using the event data. Detections are associated across time using a simple, low-cost association metric. Moreover, we collect and label a traffic dataset using the hybrid sensor DAVIS 240c. This dataset is utilized for quantitative evaluation using state-of-the-art detection and tracking metrics. We provide ground truth bounding boxes and object IDs for each vehicle annotation. Further, we generate high-temporal-resolution ground truth data to analyze tracking performance at different temporal rates. Our approach shows promising results, with minimal performance deterioration at higher temporal resolutions (48–384 Hz) when compared with the baseline frame-based performance at 24 Hz.

show abstract

Section: Related Workmentioning

confidence: 99%

“…A common approach to event-based object tracking is using clustering methods [ 25 , 26 , 31 , 34 ]. Clustering is an intuitive approach for event-based object tracking whenever there is no ego-motion applied to the camera, thus assuming that events are mainly generated around the moving objects.…”

Section: Related Workmentioning

confidence: 99%

High-Temporal-Resolution Object Detection and Tracking Using Images and Events

Shair

Rawashdeh

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…A common approach to event-based object tracking is using clustering methods [26,31,25,34]. Clustering is an intuitive way for event-based object tracking whenever there's no ego-motion applied to the camera, thus assuming that events would mainly be generated around the moving objects.…”

Section: Event-based Object Trackingmentioning

confidence: 99%

High-Temporal-Resolution Object Detection and Tracking using Images and Events

Shair¹,

Rawashdeh²

2022

Preprint

View full text Add to dashboard Cite

Event-based vision is an emerging field of computer vision that offers unique properties such as asynchronous visual output, high temporal resolutions, and dependence on brightness changes to generate data. These properties can enable robust high-temporal-resolution object detection and tracking when combined with frame-based vision. In this paper, we present a hybrid, high-temporal-resolution, object detection and tracking approach, that combines learned and classical methods using synchronized images and event data. Off-the-shelf frame-based object detectors are used for initial object detection and classification. Then, event masks, generated per each detection, are used to enable inter-frame tracking at varying temporal resolutions using the event data. Detections are associated across time using a simple low-cost association metric. Moreover, we collect and label a traffic dataset using the hybrid sensor DAVIS 240c. This dataset is utilized for quantitative evaluation using state-of-the-art detection and tracking metrics. We provide ground truth bounding boxes and object IDs for each vehicle annotation. Further, we generate high-temporal-resolution ground truth data to analyze the tracking performance at different temporal rates. Our approach shows promising results with minimal performance deterioration at higher temporal resolutions (48 – 384 Hz) when compared with the baseline frame-based performance at 24 Hz.

show abstract

“…In studies involving up to three robots, the experimental findings demonstrated 100% detection and tracking fidelity (as high as 93% for four robots) in the presence of event camera noise and robot stops. There was a gradual decline in the quality of detection and tracking as the lighting conditions changed [52]. Face Detection in Humanoid Robotic Systems as the third target reported in research works.Using design strategies like variable image scaling and simultaneous processing of many classifiers without integral picture creation, S. S. Lee et al ( 2016) created a fully pipelined architecture (Figure 6 f) that was implemented on the FPGA platform.…”

Section: P B Nithin Et Al (mentioning

confidence: 99%

The Face Detection / Recognition , Perspective and Obstacles In Robotic: A Review

Uddin

Moshayedi

et al. 2022

EAI Endorsed Trans AI Robotics

View full text Add to dashboard Cite

Facial recognition research is one of the different types of research in this world today. In recent years, facial recognition in robots has attracted increased study interest. Robotic platforms now utilize a variety of object detection methods, with face detection being a viable use. Face detection in robotics is a computer technique that recognizes human faces in digital pictures and is used in a range of applications. Different authors have performed their research in different ways on the use of detection systems. This paper aims to give future researchers a better idea of using facial recognition systems in robotics. In this study, we reviewed research by various authors over recent years to facilitate future facial recognition research. In addition, scholars have addressed the topics, how they have done so, and the specifics of their approaches are described. This paper reviewed an overview of hardware implementation and software implementation by various authors. It can automatically focus cameras or count the number of people who have entered a location. Commercial applications of the method include displaying tailored advertisements in response to a recognized face along with the algorithms, functions and architectures used in facial recognition and giving the opinions of various authors mentioned. The comparative analysis of facial recognition and its architecture system is highlighted.

show abstract

Event Camera Based Real-Time Detection and Tracking of Indoor Ground Robots

Cited by 20 publications

References 72 publications

High-Temporal-Resolution Object Detection and Tracking Using Images and Events

High-Temporal-Resolution Object Detection and Tracking Using Images and Events

High-Temporal-Resolution Object Detection and Tracking using Images and Events

The Face Detection / Recognition , Perspective and Obstacles In Robotic: A Review

Contact Info

Product

Resources

About