Abstract
Event-based cameras are not common in industrial applications despite the fact that they can add multiple advantages for applications with moving objects. In comparison with frame-based cameras, the amount of generated data is very low while keeping the main information in the scene. For an industrial environment with interconnected systems, data reduction becomes very important to avoid network congestion and provide faster response time. However, the use of new sensors as event-based cameras is not common since they do not usually provide connectivity to industrial buses. This work develops a network node based on a Field Programmable Gate Array (FPGA), including data acquisition and tracking position for an event-based camera. It also includes spurious reduction and filtering algorithms while keeping the main features at the scene. The FPGA node also includes the stack of the network protocol to provide standard communication among other nodes. The powerlink IEEE 61158 industrial network is used to communicate the FPGA with a controller connected to a self-developed two-axis servo-controlled robot. The inverse kinematics model for the robot is included in the controller. To complete the system and provide a comparison, a traditional frame-based camera is also connected to the controller. Response time and robustness to lighting conditions are tested. Results show that, using the event-based camera, the robot can follow the object using fast image recognition achieving up to 85% percent data reduction providing an average of 99 ms faster position detection and less dispersion in position detection (4.96 mm vs. 17.74 mm in the Y-axis position, and 2.18 mm vs. 8.26 mm in the X-axis position) than the frame-based camera, showing that event-based cameras are more stable under light changes. Additionally, event-based cameras offer intrinsic advantages due to the low computational complexity required: small size, low power, reduced data and low cost. Thus, it is demonstrated how the development of new equipment and algorithms can be efficiently integrated into an industrial system, merging commercial industrial equipment with new devices.
Highlights
The amount of data transmitted through communication networks is increasing at a higher pace than the supported bandwidth
Accurate and low data transfer algorithm for object tracking using an event-based camera
The proposed experimental setup was conceived to verify the two main novelties developed in this work: first, the behaviour of event-based and tracking algorithms and their advantages of implementation in an Field Programmable Gate Array (FPGA), including powerlink communication; and second, the capabilities of powerlink to provide enough speed when the Managing Node (MN) is receiving data from the FPGA
Summary
The amount of data transmitted through communication networks is increasing at a higher pace than the supported bandwidth. In industrial environments where real-time and low-latency systems are required, the saturation of communication networks due to the addition of advanced equipment generating and transmitting a high amount of data can be a problem [1]. It is possible to define if the event is caused by an intensity increment or a decrement, causing a positive or negative event. This behaviour is similar to a mammal brain [3], which leads to using neuromorphic systems [4,5] for further information processing, feature extraction, scene detection [6] and filtering [7,8]. Event-based cameras minimize light effects since only pixel intensity differences are considered and no need of specific light intensity is required, independently of light conditions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
