Comparison of the YOLOv3 and SSD MobileNet v2 Algorithms for Identifying Objects in Images from an Indoor Robotics Dataset

Object detection is a critical technology of environmental perception for autonomous driving vehicle. The Convolutional Neural Network has gradually become a powerful tool in the field of vehicle detection because of its powerful ability of feature extraction. In aiming to reach the balance between speed and accuracy of detection in complex traffic scenarios, this paper proposes an improved lightweight and high-performance vehicle–pedestrian detection algorithm based on the YOLOv4. Firstly, the backbone network CSPDarknet53 is replaced by MobileNetv2 to reduce the number of parameters and raise the capability of feature extraction. Secondly, the method of multi-scale feature fusion is used to realize the information interaction among different feature layers. Finally, a coordinate attention mechanism is added to focus on the region of interest in the image by way of weight adjustment. The experimental results show that this improved model has a great performance in vehicle–pedestrian detection in traffic scenarios. Experimental results on PASCAL VOC datasets show that the improved model’s mAP is 85.79% and speed is 35FPS, which has an increase of 4.31% and 16.7% compared to YOLOv4. Furthermore, the improved YOLOv4 model maintains a great balance between detection accuracy and speed on different datasets, indicating that it can be applied to vehicle–pedestrian detection in traffic scenarios.

show abstract

“…MobileNetv2 [ 31 , 32 ] is a lightweight backbone network proposed by Google, which is widely used in mobile and embedded devices.…”

Section: Methodsmentioning

confidence: 99%

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

Zhang

Zhou

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…During the training process, the accuracy of the three algorithm models i.e., YOLO v3 [26], Faster Region-based Convolutional Neural Network (R-CNN) [32] and Single Shot Detector (SSD) [33] in recognizing the training samples (6525) is counted when the number of iterations is 500, 1000, 1500, and 2000, respectively, to verify the detection. The statistics in Fig.…”

Section: Yolo For Pimentioning

confidence: 99%

Behavior of Delivery Robot in Human-Robot Collaborative Spaces During Navigation

Singh¹,

Kapoor²,

Abouhawwash³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Navigation is an essential skill for robots. It becomes a cumbersome task for the robot in a human-populated environment, and Industry 5.0 is an emerging trend that focuses on the interaction between humans and robots. Robot behavior in a social setting is the key to human acceptance while ensuring human comfort and safety. With the advancement in robotics technology, the true use cases of robots in the tourism and hospitality industry are expanding in number. There are very few experimental studies focusing on how people perceive the navigation behavior of a delivery robot. A robotic platform named "PI" has been designed, which incorporates proximity and vision sensors. The robot utilizes a real-time object recognition algorithm based on the You Only Look Once (YOLO) algorithm to detect objects and humans during navigation. This study is aimed towards evaluating human experience, for which we conducted a study among 36 participants to explore the perceived social presence, role, and perception of a delivery robot exhibiting different behavior conditions while navigating in a hotel corridor. The participants' responses were collected and compared for different behavior conditions demonstrated by the robot and results show that humans prefer an assistant role of a robot enabled with audio and visual aids exhibiting social behavior. Further, this study can be useful for developers to gain insight into the expected behavior of a delivery robot.

show abstract

“…Since then, Mobilenet-SSDv2 has been released, which is a combination and improvement of MobileNet and SSD [18]. In a comparison by Rios et al [19] though, it was found that Mobilenet-SSDv2 has lower recall than YoloV3. However, Mobilenet-SSDv2 is better at detecting large objects in the image compared to other detectors [20].…”

Section: B Trackingmentioning

confidence: 99%

Walk With Me: Socially Acceptable Speed and Distance Control for Mobile Wayfinding Robots

Hansen,

Clement,

Larsen

et al. 2023

2023 IEEE International Conference on Imaging Systems and Techniques (IST)

View full text Add to dashboard Cite

Robots can help people find their way around in complex buildings and environments. Robots are embodied, which makes it more intuitive for users to follow them around compared to, e.g., colored lines on the floor. However, they need to be socially intelligent for people to accept them. Like people, robots should keep a comfortable distance to its users when working.We investigate the optimization of a guiding robot's speed and distance when guiding to improve the user experience. Our findings indicate a correlation between the user's speed and the distance they keep from the robot, which can be utilized to control the robot's speed.A person tracking system is implemented on a Spot quadruped mobile robot platform from Boston Dynamics, using the on-board depth and 2D cameras plus an Intel NUC and a Jetson Nano for processing. The system uses the Mobilenet-SSDv2 CNN for user detection and Kalman filtering for tracking.Data from human-robot interaction tests on footpaths at Aalborg University is analyzed to create a linear model of the speed-distance relationship. Based on this, a control law is proposed and tested, demonstrating the ability to build a controller that allows the person following the robot to set the desired velocity of the robot.

show abstract

Comparison of the YOLOv3 and SSD MobileNet v2 Algorithms for Identifying Objects in Images from an Indoor Robotics Dataset

Cited by 18 publications

References 7 publications

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

Behavior of Delivery Robot in Human-Robot Collaborative Spaces During Navigation

Walk With Me: Socially Acceptable Speed and Distance Control for Mobile Wayfinding Robots

Contact Info

Product

Resources

About