A Machine Vision-Based Method Optimized for Restoring Broiler Chicken Images Occluded by Feeding and Drinking Equipment

Abstract

The presence equipment (e.g., water pipes, feed buckets, and other presence equipment, etc.) in the poultry house can occlude the areas of broiler chickens taken via top view. This can affect the analysis of chicken behaviors through a vision-based machine learning imaging method. In our previous study, we developed a machine vision-based method for monitoring the broiler chicken floor distribution, and here we processed and restored the areas of broiler chickens which were occluded by presence equipment. To verify the performance of the developed restoration method, a top-view video of broiler chickens was recorded in two research broiler houses (240 birds equally raised in 12 pens per house). First, a target detection algorithm was used to initially detect the target areas in each image, and then Hough transform and color features were used to remove the occlusion equipment in the detection result further. In poultry images, the broiler chicken occluded by equipment has either two areas (TA) or one area (OA). To reconstruct the occluded area of broiler chickens, the linear restoration method and the elliptical fitting restoration method were developed and tested. Three evaluation indices of the overlap rate (OR), false-positive rate (FPR), and false-negative rate (FNR) were used to evaluate the restoration method. From images collected on d2, d9, d16, and d23, about 100-sample images were selected for testing the proposed method. And then, around 80 high-quality broiler areas detected were further evaluated for occlusion restoration. According to the results, the average value of OR, FPR, and FNR for TA was 0.8150, 0.0032, and 0.1850, respectively. For OA, the average values of OR, FPR, and FNR were 0.8788, 0.2227, and 0.1212, respectively. The study provides a new method for restoring occluded chicken areas that can hamper the success of vision-based machine predictions.

Design and Application of Art Education Communication Platform Based on Machine Vision

“…e main features of machine vision are as follows: (1) e system selects workpiece of different sizes according to the operator, calls the corresponding visual program for size detection, and outputs the results; (2) the system can monitor the detection process by displaying images or dynamically view the detection results through the detection data displayed on the interface; (3) it has the function of timely and accurately sending out control signals and eliminating waste products to the wrong workpiece; (4) the model can display the detection screen in real time, and has the function of storing and viewing the image of the error workpiece in real time.…”

“…Machine vision has broad application prospects in different fields: graph optimization processing [1], sensors [2], sound source reconstruction [3], visual prediction [4], and pollution monitoring [5]. In view of a series of problems existing in the process of maize species analysis based on machine vision theory, the authenticity analysis method was introduced to obtain an optimized machine vision analysis model [6].…”

Automatic detection of brown hens in cage-free houses with deep learning methods

“…Computer vision technologies ( CVTs ) have been applied to monitor animals’ behaviors and performance ( Guo et al, 2020 , 2021a , 2021b , 2022 ; Qiao et al, 2022 ; Li et al, 2021 a; Bist et al, 2023a ). The CVT-based methods can avoid human observation errors and monitor animal information quickly, accurately, and efficiently which is of great significance to the large-scale poultry production environments.…”

Monitoring Behaviors of Broiler Chickens at Different Ages with Deep Learning

“…Non-contact monitoring methods are usually based on animal images/videos or audio to extract relevant features and build behavior recognition models. In addition, computer vision technology has been widely used in non-contact monitoring in animal farming [ 9 , 10 , 11 ]. Traditional computer vision technology is used to extract artificially designed features (e.g., color, shape, and texture) from images or videos and combine machine learning algorithms for recognizing animal behaviors.…”

“…The recognition accuracy depends on the feature extraction method. In addition, external factors such as complex scenes, occlusion between animals, and light intensity impact the extraction efficiency of animal features, thereby affecting the accuracy of behavior recognition [ 10 ].…”