Dual-Stream Fusion Network with ConvNeXtV2 for Pig Weight Estimation Using RGB-D Data in Aisles

Simple Summary In the realm of livestock management, accurately estimating the weight of pigs presents a critical yet challenging task, particularly in the dynamic environment of farms. Traditional methods often struggle due to the continuous movement of pigs and fluctuating conditions such as lighting. To address these challenges, our study focuses on developing a novel method that simplifies weight estimation while adapting to the constantly changing conditions of real-world pig farms. Our solution, the moving pig weight estimate algorithm based on deep vision (MPWEADV), marks a significant step in this direction. It employs advanced imaging technology to capture both the visual appearance and depth information of moving pigs. The central idea is to combine these two types of data for more accurate weight estimates than traditional methods could provide. To validate our proposed method, we replicated two recently published methods and demonstrated through experimental results that our pig weight estimation model could rapidly and accurately determine the weight of pigs in the challenging scenarios we constructed. This model operates in an unconstrained environment, providing real-time evaluation of pigs' weight, thereby offering data support for grading and adjusting breeding plans, indicating a wide range of potential applications.Abstract In the field of livestock management, noncontact pig weight estimation has advanced considerably with the integration of computer vision and sensor technologies. However, real-world agricultural settings present substantial challenges for these estimation techniques, including the impacts of variable lighting and the complexities of measuring pigs in constant motion. To address these issues, we have developed an innovative algorithm, the moving pig weight estimate algorithm based on deep vision (MPWEADV). This algorithm effectively utilizes RGB and depth images to accurately estimate the weight of pigs on the move. The MPWEADV employs the advanced ConvNeXtV2 network for robust feature extraction and integrates a cutting-edge feature fusion module. Supported by a confidence map estimator, this module effectively merges information from both RGB and depth modalities, enhancing the algorithm's accuracy in determining pig weight. To demonstrate its efficacy, the MPWEADV achieved a root-mean-square error (RMSE) of 4.082 kg and a mean absolute percentage error (MAPE) of 2.383% in our test set. Comparative analyses with models replicating the latest research show the potential of the MPWEADV in unconstrained pig weight estimation practices. Our approach enables real-time assessment of pig conditions, offering valuable data support for grading and adjusting breeding plans, and holds broad prospects for application.