Evaluation of low-cost depth cameras for agricultural applications

Condotta, Isabella C. F. S.; Brown–Brandl, T. M.; Pitla, Santosh K.; Stinn, John P.; Miranda, Késia Oliveira da Silva

doi:10.1016/j.compag.2020.105394

Cited by 65 publications

(32 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the distance between the camera and the floor was 2.25 m, which made it possible to capture the entire pen. Previous studies have reported shorter distances than that utilized in the present study, for example, 1.7 m above the ground ( Condotta et al, 2020 ) or 1.0–1.2 m above the pig ( Pezzuolo et al, 2018a ). A longer camera clamp may be required to reduce the distance to be either equal to or less than 2 m in future experiments to obtain more accurate depth data.…”

Section: Discussionmentioning

confidence: 53%

“…The second factor was the distance between the sensor and the pig. It has been reported that random error measurements increase with increasing distance between the sensor and the object ( Condotta et al, 2020 ). In this study, the distance between the camera and the floor was 2.25 m, which made it possible to capture the entire pen.…”

Section: Discussionmentioning

confidence: 99%

“…This type of depth-sensing camera, also known as RGB-D camera if a red, green, and blue (RGB) sensor is jointly equipped, has been recently used to estimate the mass and size of pigs. For example, applications of these depth cameras include the ASUS Xtion series ( Wang et al, 2018 , 2019 ), Microsoft Kinect series ( Kongsro 2014 ; Condotta et al, 2018 , 2020 ; Pezzuolo et al, 2018a ; Fernandes et al, 2019 ), and Intel RealSense series ( Condotta et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera

Hyeong-keun

Lee

Morota

2021

Translational Animal Science

View full text Add to dashboard Cite

Average daily gain is an indicator of the growth rate, feed efficiency, and current health status of livestock species including pigs. Continuous monitoring of daily gain in pigs aids producers to optimize their growth performance while ensuring animal welfare and sustainability, such as reducing stress reactions and feed waste. Computer vision has been used to predict live body weight from video images without direct handling of the pig. In most studies, videos were taken while pigs were immobilized at a weighing station or feeding area to facilitate data collection. An alternative approach is to capture videos while pigs are allowed to move freely within their own housing environment, which can be easily applied to production system as no special imaging station needs to be established. The objective of this study was to establish a computer vision system by collecting RGB-D videos to capture top-view RGB and depth images of non-restrained, growing pigs to predict their body weight over time. Over a period of 38 days, eight growers were video recorded for approximately 3 min per day, at the rate of six frames per second, and manually weighed using an electronic scale. An image-processing pipeline in Python using OpenCV was developed to process the images. Specifically, each pig within the RGB frame was segmented by a thresholding algorithm, and the contour of the pig was identified to extract its length and width. The height of a pig was estimated from the depth images captured by the infrared depth sensor. Quality control included removing pigs that were touching the fence and sitting, as well as those showing extremely distorted shape or motion blur owing to their frequent movement. Fitting all of the morphological image descriptors simultaneously in linear mixed models yielded prediction coefficients of determination of 0.72–0.98, 0.65–0.95, 0.51–0.94, and 0.49–0.93 for one-, two-, three-, and four-day ahead forecasting, respectively, of body weight in time series cross-validation. Based on the results, we conclude that our RGB-D sensor-based imaging system coupled with the Python image-processing pipeline could potentially provide an effective approach to predict the live body weight of non-restrained pigs from images.

show abstract

Section: Discussionmentioning

confidence: 53%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera

Hyeong-keun

Lee

Morota

2021

Translational Animal Science

View full text Add to dashboard Cite

show abstract

“…Low-cost consumer 3D depth-sensor cameras, such as Microsoft Kinect (Microsoft, Redmond, WA) and Intel RealSense (Intel, Santa Clara, CA), have been used to predict morphological characters and monitor animal behavior ( Condotta et al, 2020 ). A depth-sensor camera positioned at the ceiling visualizes animals in a 3D space by adding height information using the time-of-flight or structured light technology.…”

Section: Computer Visionmentioning

confidence: 99%

ASAS-NANP SYMPOSIUM: prospects for interactive and dynamic graphics in the era of data-rich animal science1

Morota

Cheng

Cook

et al. 2021

Journal of Animal Science

View full text Add to dashboard Cite

Statistical graphics, and data visualization, play an essential but under-utilized, role for data analysis in animal science, and also to visually illustrate the concepts, ideas, or outputs of research and in curricula. The recent rise in web technologies and ubiquitous availability of web browsers enables easier sharing of interactive and dynamic graphics. Interactivity and dynamic feedback enhance human–computer interaction and data exploration. Web applications such as decision support systems coupled with multimedia tools synergize with interactive and dynamic graphics. However, the importance of graphics for effectively communicating data, understanding data uncertainty, and the state of the field of interactive and dynamic graphics is underappreciated in animal science. To address this gap, we describe the current state of graphical methodology and technology that might be more broadly adopted. This includes an explanation of a conceptual framework for effective graphics construction. The ideas and technology are illustrated using publicly available animal datasets. We foresee that many new types of big and complex data being generated in precision livestock farming create exciting opportunities for applying interactive and dynamic graphics to improve data analysis and make data-supported decisions.

show abstract

“…Desspite superior performance on Visual Odometry (VO), other works present the relevant errors in many applications when comparing point clouds’ accuracy generated from structured light and stereo sensors. In [ 41 ], several cameras are analyzed and compared in length and area accuracy in terms of pixel coefficients. Even though the ZED camera presents good and sometimes the best results in outdoor applications, there are more flaws and inaccuracies in close objects, with depth deviations that lead to wrong measurements of volume and area.…”

Section: 3d Reconstruction Heterogeneous Edge Environments and Rmentioning

confidence: 99%

A Heterogeneous Edge-Fog Environment Supporting Digital Twins for Remote Inspections

Silva

Vidal

Honório

et al. 2020

Sensors

View full text Add to dashboard Cite

The increase in the development of digital twins brings several advantages to inspection and maintenance, but also new challenges. Digital models capable of representing real equipment for full remote inspection demand the synchronization, integration, and fusion of several sensors and methodologies such as stereo vision, monocular Simultaneous Localization and Mapping (SLAM), laser and RGB-D camera readings, texture analysis, filters, thermal, and multi-spectral images. This multidimensional information makes it possible to have a full understanding of given equipment, enabling remote diagnosis. To solve this problem, the present work uses an edge-fog-cloud architecture running over a publisher-subscriber communication framework to optimize the computational costs and throughput. In this approach, each process is embedded in an edge node responsible for prepossessing a given amount of data that optimizes the trade-off of processing capabilities and throughput delays. All information is integrated with different levels of fog nodes and a cloud server to maximize performance. To demonstrate this proposal, a real-time 3D reconstruction problem using moving cameras is shown. In this scenario, a stereo and RDB-D cameras run over edge nodes, filtering, and prepossessing the initial data. Furthermore, the point cloud and image registration, odometry, and filtering run over fog clusters. A cloud server is responsible for texturing and processing the final results. This approach enables us to optimize the time lag between data acquisition and operator visualization, and it is easily scalable if new sensors and algorithms must be added. The experimental results will demonstrate precision by comparing the results with ground-truth data, scalability by adding further readings and performance.

show abstract

Evaluation of low-cost depth cameras for agricultural applications

Cited by 65 publications

References 24 publications

Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera

Forecasting dynamic body weight of nonrestrained pigs from images using an RGB-D sensor camera

ASAS-NANP SYMPOSIUM: prospects for interactive and dynamic graphics in the era of data-rich animal science1

A Heterogeneous Edge-Fog Environment Supporting Digital Twins for Remote Inspections

Contact Info

Product

Resources

About