scholarly journals Feasibility Research on Fish Pose Estimation Based on Rotating Box Object Detection

Fishes ◽  
2021 ◽  
Vol 6 (4) ◽  
pp. 65
Author(s):  
Bin Lin ◽  
Kailin Jiang ◽  
Zhiqi Xu ◽  
Feiyi Li ◽  
Jiao Li ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Animal Behavior ◽  
Deep Neural Networks ◽  
Physiological State ◽  
Estimation Model ◽  
Algorithm Performance ◽  
Feasibility Research ◽  
Underwater Environment ◽  
Key Points ◽  
Underwater Camera

A video-based method to quantify animal posture movement is a powerful way to analyze animal behavior. Both humans and fish can judge the physiological state through the skeleton framework. However, it is challenging for farmers to judge the breeding state in the complex underwater environment. Therefore, images can be transmitted by the underwater camera and monitored by a computer vision model. However, it lacks datasets in artificial intelligence and is unable to train deep neural networks. The main contributions of this paper include: (1) the world’s first fish posture database is established. 10 key points of each fish are manually marked. The fish flock images were taken in the experimental tank and 1000 single fish images were separated from the fish flock. (2) A two-stage attitude estimation model is used to detect fish key points. The evaluation of the algorithm performance indicates the precision of detection reaches 90.61%, F1-score reaches 90%, and Fps also reaches 23.26. We made a preliminary exploration on the pose estimation of fish and provided a feasible idea for fish pose estimation.

scholarly journals Real-time, low-latency closed-loop feedback using markerless posture tracking

2020 ◽  
Author(s):  
Gary Kane ◽  
Gonçalo Lopes ◽  
Jonny L. Saunders ◽  
Alexander Mathis ◽  
Mackenzie W. Mathis
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Deep Neural Networks ◽  
Low Latency ◽  
Forward Prediction ◽  
Prediction Module ◽  
Wide Range ◽  
Loop Feedback ◽  
Closed Loop Feedback

AbstractThe ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here we provide a new DeepLabCut-Live! package that achieves low-latency real-time pose estimation (within 15 ms, >100 FPS), with an additional forward-prediction module that achieves zero-latency feedback, and a dynamic-cropping mode that allows for higher inference speeds. We also provide three options for using this tool with ease: (1) a stand-alone GUI (called DLC-Live! GUI), and integration into (2) Bonsai and (3) AutoPilot. Lastly, we benchmarked performance on a wide range of systems so that experimentalists can easily decide what hardware is required for their needs.

scholarly journals Real-time, low-latency closed-loop feedback using markerless posture tracking

eLife ◽  
2020 ◽  
Vol 9 ◽  
Author(s):  
Gary A Kane ◽  
Gonçalo Lopes ◽  
Jonny L Saunders ◽  
Alexander Mathis ◽  
Mackenzie W Mathis
Keyword(s):  
Real Time ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Deep Neural Networks ◽  
Low Latency ◽  
Forward Prediction ◽  
Prediction Module ◽  
Wide Range ◽  
Loop Feedback ◽  
Closed Loop Feedback

The ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here, we provide a new <monospace>DeepLabCut-Live!</monospace> package that achieves low-latency real-time pose estimation (within 15 ms, >100 FPS), with an additional forward-prediction module that achieves zero-latency feedback, and a dynamic-cropping mode that allows for higher inference speeds. We also provide three options for using this tool with ease: (1) a stand-alone GUI (called <monospace>DLC-Live! GUI</monospace>), and integration into (2) <monospace>Bonsai,</monospace> and (3) <monospace>AutoPilot</monospace>. Lastly, we benchmarked performance on a wide range of systems so that experimentalists can easily decide what hardware is required for their needs.

scholarly journals DeepTravel: a Neural Network Based Travel Time Estimation Model with Auxiliary Supervision

2018 ◽  
Author(s):  
Hanyuan Zhang ◽  
Hao Wu ◽  
Weiwei Sun ◽  
Baihua Zheng
Keyword(s):  
Travel Time ◽  
Deep Neural Networks ◽  
Time Estimation ◽  
Travel Time Estimation ◽  
Urban Mobility ◽  
Time Cost ◽  
Trajectory Data ◽  
Estimation Model ◽  
New Development ◽  
Supervision Model

Estimating the travel time of a path is of great importance to smart urban mobility. Existing approaches are either based on estimating the time cost of each road segment which are not able to capture many cross-segment complex factors, or designed heuristically in a non-learning-based way which fail to leverage the natural abundant temporal labels of the data, i.e., the time stamp of each trajectory point. In this paper, we leverage on new development of deep neural networks and propose a novel auxiliary supervision model, namely DeepTravel, that can automatically and effectively extract different features, as well as make full use of the temporal labels of the trajectory data. We have conducted comprehensive experiments on real datasets to demonstrate the out-performance of DeepTravel over existing approaches. 

scholarly journals SIPEC: the deep-learning Swiss knife for behavioral data analysis

2020 ◽  
Author(s):  
Markus Marks ◽  
Jin Qiuhan ◽  
Oliver Sturman ◽  
Lukas von Ziegler ◽  
Sepp Kollmorgen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Animal Behavior ◽  
Home Cage ◽  
Complex Environments ◽  
Or Groups ◽  
Multiple Behaviors ◽  
Freely Moving ◽  
Using Data

ABSTRACTAnalysing the behavior of individuals or groups of animals in complex environments is an important, yet difficult computer vision task. Here we present a novel deep learning architecture for classifying animal behavior and demonstrate how this end-to-end approach can significantly outperform pose estimation-based approaches, whilst requiring no intervention after minimal training. Our behavioral classifier is embedded in a first-of-its-kind pipeline (SIPEC) which performs segmentation, identification, pose-estimation and classification of behavior all automatically. SIPEC successfully recognizes multiple behaviors of freely moving mice as well as socially interacting nonhuman primates in 3D, using data only from simple mono-vision cameras in home-cage setups.

scholarly journals A peduncle detection method of tomato for autonomous harvesting

2021 ◽  
Author(s):  
Jiacheng Rong ◽  
Guanglin Dai ◽  
Pengbo Wang
Keyword(s):  
Pose Estimation ◽  
Pitch Angle ◽  
Detection Method ◽  
Geometric Model ◽  
Average Error ◽  
Long Distance ◽  
End Effector ◽  
Key Points ◽  
Yaw Angle ◽  
Cutting Point

AbstractFor automating the harvesting of bunches of tomatoes in a greenhouse, the end-effector needs to reach the exact cutting point and adaptively adjust the pose of peduncles. In this paper, a method is proposed for peduncle cutting point localization and pose estimation. Images captured in real time at a fixed long-distance are detected using the YOLOv4-Tiny detector with a precision of 92.7% and a detection speed of 0.0091 s per frame, then the YOLACT +  + Network with mAP of 73.1 and a time speed of 0.109 s per frame is used to segment the close-up distance. The segmented peduncle mask is fitted to the curve using least squares and three key points on the curve are found. Finally, a geometric model is established to estimate the pose of the peduncle with an average error of 4.98° in yaw angle and 4.75° in pitch angle over the 30 sets of tests.

Feeding critically ill patients: current concepts

2001 ◽  
Vol 21 (4) ◽  
pp. 60-69 ◽  
Author(s):  
EB Trujillo ◽  
MK Robinson ◽  
DO Jacobs
Keyword(s):  
Critically Ill ◽  
Critically Ill Patients ◽  
Nutrient Intake ◽  
Nutritional Support ◽  
Physiological State ◽  
Support Service ◽  
Critical Care Nurses ◽  
Metabolic Complications ◽  
Key Points ◽  
Early Use

Provision of nutritional support to critically ill patients can be challenging. Critical care nurses must be aware of which patients require specific nutritional support, when to initiate nutritional support, and by which route to provide nutritional support. Consultation with a dietitian or nutritional support service can help facilitate this process. The key points in addressing these questions are (1) the nutritional status of the patient or the length of time he or she has been without significant nutrient intake, (2) whether the patient has a hypermetabolic condition that warrants the early use of nutritional support, and (3) the function of the patient's gastrointestinal tract. What to feed depends on the physiological state of the patient. Adjusting the nutrient composition of the feeding solution may prevent metabolic complications and may improve the overall outcome for the patient.

scholarly journals Long-Range Pose Estimation for Aerial Refueling Approaches Using Deep Neural Networks

2020 ◽  
Vol 17 (11) ◽  
pp. 634-646
Author(s):  
Andrew Lee ◽  
Will Dallmann ◽  
Scott Nykl ◽  
Clark Taylor ◽  
Brett Borghetti
Keyword(s):  
Neural Networks ◽  
Long Range ◽  
Pose Estimation ◽  
Deep Neural Networks ◽  
Aerial Refueling

scholarly journals Model Free Localization with Deep Neural Architectures by Means of an Underwater WSN

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3530
Author(s):  
Juan Parras ◽  
Santiago Zazo ◽  
Iván A. Pérez-Álvarez ◽  
José Luis Sanz González
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Acoustic Signals ◽  
Model Free ◽  
Underwater Environment ◽  
The Neural Network ◽  
Anchor Nodes ◽  
Localization Precision ◽  
Significant Effort ◽  
Localization Systems

In recent years, there has been a significant effort towards developing localization systems in the underwater medium, with current methods relying on anchor nodes, explicitly modeling the underwater channel or cooperation from the target. Lately, there has also been some work on using the approximation capabilities of Deep Neural Networks in order to address this problem. In this work, we study how the localization precision of using Deep Neural Networks is affected by the variability of the channel, the noise level at the receiver, the number of neurons of the neural network and the utilization of the power or the covariance of the received acoustic signals. Our study shows that using deep neural networks is a valid approach when the channel variability is low, which opens the door to further research in such localization methods for the underwater environment.

Sign in / Sign up

Export Citation Format

Share Document