It is crucial to monitor the status of aquaculture objects in recirculating aquaculture systems (RASs). Due to their high density and a high degree of intensification, aquaculture objects in such systems need to be monitored for a long time period to prevent losses caused by various factors. Object detection algorithms are gradually being used in the aquaculture industry, but it is difficult to achieve good results for scenes with high density and complex environments. This paper proposes a monitoring method for Larimichthys crocea in a RAS, which includes the detection and tracking of abnormal behavior. The improved YOLOX-S is used to detect Larimichthys crocea with abnormal behavior in real time. Aiming to solve the problems of stacking, deformation, occlusion, and too-small objects in a fishpond, the object detection algorithm used is improved by modifying the CSP module, adding coordinate attention, and modifying the part of the structure of the neck. After improvement, the AP50 reaches 98.4% and AP50:95 is also 16.2% higher than the original algorithm. In terms of tracking, due to the similarity in the fish’s appearance, Bytetrack is used to track the detected objects, avoiding the ID switching caused by re-identification using appearance features. In the actual RAS environment, both MOTA and IDF1 can reach more than 95% under the premise of fully meeting real-time tracking, and the ID of the tracked Larimichthys crocea with abnormal behavior can be maintained stably. Our work can identify and track the abnormal behavior of fish efficiently, and this will provide data support for subsequent automatic treatment, thus avoiding loss expansion and improving the production efficiency of RASs.
It is urgently desired to develop high-performance wind energy collectors to power numerous microelectronic devices along with the Internet of Things (IoT). A roller-type triboelectric nanogenerator (R-TENG) based on rotational friction between wool and stacked interfaces is proposed and efficiently used for harvesting wind energy. Wool, an electropositive and flexible material, is utilized in the design, effectively reducing abrasion on the contact surface and adjusting the output in response to varying compression levels. The conductive layer greatly enhances the output performance, which produces more induced charge by stacking different triboelectric materials in a particular order. By adding bottom power generation units, the internal space of the unit can be fully utilized to improve its energy conversion efficiency. At 900 rpm of the motor, the instantaneous open-circuit voltage (VOC), short-circuit current (ISC), and transferred charge (QSC) of the R-TENG can reach 1504 V, 67.24 μA and 157.4 nC, respectively. After connection to a load via a rectifier bridge, the R-TENG has a maximum power output of 14.58 mW and an instantaneous power density of 11.7 W m−3. In laboratory wind energy harvesting experiments, the design can easily drive at least 720 LEDs and charge a 2000 μF capacitor up to about 1.5 V in 78 s. In practice, the R-TENG can collect natural wind on windy seashores and moving vehicles to charge capacitors and successfully drive small electronic devices in real time. The experimental results indicate that the stacked PTFE/FKM/Wool R-TENG exhibits considerable output performance, making it a promising solution for efficiently capturing wind energy from all directions.