1
|
Doornweerd JE, Kootstra G, Veerkamp RF, Ellen ED, van der Eijk JAJ, van de Straat T, Bouwman AC. Across-Species Pose Estimation in Poultry Based on Images Using Deep Learning. FRONTIERS IN ANIMAL SCIENCE 2021. [DOI: 10.3389/fanim.2021.791290] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Animal pose-estimation networks enable automated estimation of key body points in images or videos. This enables animal breeders to collect pose information repeatedly on a large number of animals. However, the success of pose-estimation networks depends in part on the availability of data to learn the representation of key body points. Especially with animals, data collection is not always easy, and data annotation is laborious and time-consuming. The available data is therefore often limited, but data from other species might be useful, either by itself or in combination with the target species. In this study, the across-species performance of animal pose-estimation networks and the performance of an animal pose-estimation network trained on multi-species data (turkeys and broilers) were investigated. Broilers and turkeys were video recorded during a walkway test representative of the situation in practice. Two single-species and one multi-species model were trained by using DeepLabCut and tested on two single-species test sets. Overall, the within-species models outperformed the multi-species model, and the models applied across species, as shown by a lower raw pixel error, normalized pixel error, and higher percentage of keypoints remaining (PKR). The multi-species model had slightly higher errors with a lower PKR than the within-species models but had less than half the number of annotated frames available from each species. Compared to the single-species broiler model, the multi-species model achieved lower errors for the head, left foot, and right knee keypoints, although with a lower PKR. Across species, keypoint predictions resulted in high errors and low to moderate PKRs and are unlikely to be of direct use for pose and gait assessments. A multi-species model may reduce annotation needs without a large impact on performance for pose assessment, however, with the recommendation to only be used if the species are comparable. If a single-species model exists it could be used as a pre-trained model for training a new model, and possibly require a limited amount of new data. Future studies should investigate the accuracy needed for pose and gait assessments and estimate genetic parameters for the new phenotypes before pose-estimation networks can be applied in practice.
Collapse
|
2
|
The relationship between gait and automated recordings of individual broiler activity levels. Poult Sci 2021; 100:101300. [PMID: 34280651 PMCID: PMC8318892 DOI: 10.1016/j.psj.2021.101300] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2020] [Revised: 05/26/2021] [Accepted: 05/26/2021] [Indexed: 12/02/2022] Open
Abstract
Gait, or walking ability, is an often-measured trait in broilers. Individual gait scores are generally determined manually, which can be time-consuming and subjective. Automated methods of scoring gait are available, but are often implemented at the group level. However, there is an interest in automated methods of scoring gait at the individual level. We hypothesized that locomotor activity could serve as a proxy for gait of individual broilers. Locomotor activity of 137 group-housed broilers from four crosses was recorded from approximately 16 to 32 days old, using an ultra-wideband tracking system. These birds were divided over four trials. Individual gait scores were determined at the end of the tracking period, on a scale from 0 to 5, with higher scores representing worse gait. Given the limited number of birds, birds were subsequently categorized as having a good gait (GG; scores 0–2) or a suboptimal gait (SG; scores 3–5). Relationships between activity and gait classification were studied to determine whether individual activity has the potential to serve as a proxy for gait. When comparing GG and SG birds using robust linear regression, SG birds showed a lower 1) activity around the start of tracking (estimate = −1.33 ± 0.56, P = 0.019), 2) activity near the end of tracking (estimate = −1.63 ± 0.38, P < 0.001), and 3) average activity (estimate = −1.12 ± 0.41, P = 0.007). When taking day of tracking, trial, cross and body weight category (heavy versus light at approximately 2 wk old) into account, a tendency was still observed for SG birds having lower activity levels within lightweight birds, but not within heavyweight birds. This study provides indications for activity differences between gait classifications. However, given that there was considerable overlap in activity levels between the gait classifications, future research implementing additional activity-related variables is required to allow a more complete distinction between birds with different gait classifications.
Collapse
|
3
|
Darbandi H, Serra Bragança F, van der Zwaag BJ, Voskamp J, Gmel AI, Haraldsdóttir EH, Havinga P. Using Different Combinations of Body-Mounted IMU Sensors to Estimate Speed of Horses-A Machine Learning Approach. SENSORS 2021; 21:s21030798. [PMID: 33530288 PMCID: PMC7865839 DOI: 10.3390/s21030798] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/17/2020] [Revised: 01/08/2021] [Accepted: 01/20/2021] [Indexed: 12/13/2022]
Abstract
Speed is an essential parameter in biomechanical analysis and general locomotion research. It is possible to estimate the speed using global positioning systems (GPS) or inertial measurement units (IMUs). However, GPS requires a consistent signal connection to satellites, and errors accumulate during IMU signals integration. In an attempt to overcome these issues, we have investigated the possibility of estimating the horse speed by developing machine learning (ML) models using the signals from seven body-mounted IMUs. Since motion patterns extracted from IMU signals are different between breeds and gaits, we trained the models based on data from 40 Icelandic and Franches-Montagnes horses during walk, trot, tölt, pace, and canter. In addition, we studied the estimation accuracy between IMU locations on the body (sacrum, withers, head, and limbs). The models were evaluated per gait and were compared between ML algorithms and IMU location. The model yielded the highest estimation accuracy of speed (RMSE = 0.25 m/s) within equine and most of human speed estimation literature. In conclusion, highly accurate horse speed estimation models, independent of IMU(s) location on-body and gait, were developed using ML.
Collapse
Affiliation(s)
- Hamed Darbandi
- Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The Netherlands; (B.J.v.d.Z.); (P.H.)
- Correspondence:
| | - Filipe Serra Bragança
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, 3584 CM Utrecht, The Netherlands;
| | - Berend Jan van der Zwaag
- Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The Netherlands; (B.J.v.d.Z.); (P.H.)
- Inertia Technology B.V., 7521 AG Enschede, The Netherlands
| | - John Voskamp
- Rosmark Consultancy, 6733 AA Wekerom, The Netherlands;
| | - Annik Imogen Gmel
- Equine Department, Vetsuisse Faculty, University of Zurich, 8057 Zurich, Switzerland; (A.I.G.); (E.H.H.)
- Agroscope—Swiss National Stud Farm, Les Longs-Prés, 1580 Avenches, Switzerland
| | - Eyrún Halla Haraldsdóttir
- Equine Department, Vetsuisse Faculty, University of Zurich, 8057 Zurich, Switzerland; (A.I.G.); (E.H.H.)
| | - Paul Havinga
- Pervasive Systems Group, Department of Computer Science, University of Twente, 7522 NB Enschede, The Netherlands; (B.J.v.d.Z.); (P.H.)
| |
Collapse
|
4
|
Xia R, Wang G, Zhang Y, Yang P, Yang Z, Ding S, Jia X, Yang C, Liu C, Ma S, Lin J, Wang X, Hou X, Zhang K, Gao X, Duan P, Qian C. River algal blooms are well predicted by antecedent environmental conditions. WATER RESEARCH 2020; 185:116221. [PMID: 32731076 DOI: 10.1016/j.watres.2020.116221] [Citation(s) in RCA: 28] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/02/2020] [Revised: 07/02/2020] [Accepted: 07/22/2020] [Indexed: 06/11/2023]
Abstract
River algal blooms have become a challenging environmental problem worldwide due to strong interference of human activities and megaprojects (e.g., big dams and large-scale water transfer projects). Previous studies on algal blooms were mainly focused on relatively static water bodies (i.e., lakes and reservoirs), but less on the large rivers. As the largest tributary of the Yangtze River of China and the main freshwater source of the South-to-North Water Diversion Project (SNWDP), the Han River has experienced frequent algal blooms in recent decades. Here we investigated the algal blooms during a decade (2003-2014) in the Han River by two gradient boosting machine (GBM) models with k-fold cross validation, which used explanatory variables from current 10-day (GBMc model) or previous 10-day period (GBMp model). Our results advocate the use of GBMp due to its higher accuracy (median Kappa = 0.9) and practical predictability (using antecedent observations) compared to GBMc. We also revealed that the algal blooms in the Han River were significantly modulated by antecedent water levels in the Han River and the Yangtze River and water level variation in the Han River, whereas the nutrient concentrations in the Han River were usually above thresholds and not limiting algal blooms. This machine-learning-based study potentially provides scientific guidance for preemptive warning and risk management of river algal blooms through comprehensive regulation of water levels during the dry season by making use of water conservancy measures in large rivers.
Collapse
Affiliation(s)
- Rui Xia
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Gangsheng Wang
- State Key Laboratory of Water Resources and Hydropower Engineering Sciences, Wuhan University, Wuhan 430072, China; Institute for Environmental Genomics, University of Oklahoma, Norman, OK 73019, USA.
| | - Yuan Zhang
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Peng Yang
- School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China
| | - Zhongwen Yang
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Sen Ding
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Xiaobo Jia
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Chen Yang
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Chengjian Liu
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Shuqin Ma
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Jianing Lin
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Xiao Wang
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Xikang Hou
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Kai Zhang
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Xin Gao
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Pingzhou Duan
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| | - Chang Qian
- State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China
| |
Collapse
|