Across-Species Pose Estimation in Poultry Based on Images Using Deep Learning

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.

Real-Time Rendering Algorithm Based On Hybrid Static And Dynamic Simplification Methods

Level of detail (LoD) method is a key technique for real-time rendering. The generation algorithms of LoD models may be divided into two categories: static or view-independent algorithms and dynamic or view-dependent algorithms, each has its own advantages and drawbacks. This paper presents a new realtime rendering algorithm incorporating both of the two kinds. We simplify polygonal models viewindependently according to a user-specified approximation error first. Then the simplified models are used in a view-dependent real-time rendering algorithm. The paper presents a new view-dependent realtime mesh simplification algorithm. The algorithm can produce simplified models in real time while controlling the rendering pixel error. Examples illustrate efficiency of the algorithm.

Determination of a Gain-Function Relating Control Force to Cursor Velocity

F-14D fighter pilots will have the capability to use cursor control to designate symbols and pushbutton legends on multifunction displays (MFD). Since operators often will be required to slew and designate a target symbol or pushbutton legend in diverse environments, it is important to determine a control system gain, the relationship between response magnitude (in this case, force) and amount of cursor movement or velocity, that will enhance performance during slewing/designate tasks. The purpose of this study was to evaluate six different gain-functions analyzing speed, accuracy, and subjective comments, to determine an optimal gain-function relating control force to cursor velocity. Trend indicated that Gain-function 1, the gain-function with the lowest mean pixel error and fastest mean acquisition time, would be the best gain-function to use in the F-14D aircraft.