Feng Liu

To achieve non-contact and continuous monitoring of body length in Micropterus salmoides and overcome the stress damage and subjective error associated with traditional manual measurement, this paper proposes an improved YOLOv8-based multi-target tracking framework for intensive recirculating aquaculture systems. The system employs a geometric measurement framework based on monocular vision that achieves conversion from pixel coordinates to actual body length through camera calibration, water-surface refraction correction, and pose projection correction. Under a collaborative optimization framework integrating detection and tracking, the model incorporates multi-scale feature enhancement, lightweight re-identification (ReID), and a robust data association mechanism, which improves system stability under conditions of high fish density, variable illumination, and turbid water. A shallow feature fusion path is introduced to enhance small-target perception, and a MobileNetV3_ReID model is adopted to extract highly discriminative appearance features, which improves identity consistency while maintaining model compactness. In the data association stage, a hybrid cost matrix integrating IoU, cosine similarity, and motion consistency is constructed, and optimal matching is realized through the Hungarian algorithm. Dynamic threshold adjustment and an exponential moving-average feature-update strategy are introduced to effectively suppress identity switching. Experiments were conducted on an overhead video dataset of Micropterus salmoides collected at a recirculating aquaculture system facility. The results show that the proposed method achieves 82.7% mAP50 while maintaining a real-time throughput of 88 FPS, with MOTA reaching 76.9% and IDF1 reaching 81.5%—the latter representing an improvement of 3.2 percentage points over BoT-SORT and 5.3 percentage points over the YOLOv8 baseline tracker. The number of identity switches (IDSW) decreased from 89 in the baseline configuration to 39, a reduction of 56.2%. Crucially, these component-level improvements translate into a body length error (BLE) of 5.2 ± 1.8% (MAE = 1.35 cm, Pearson r = 0.972), representing a 38.8% improvement over the baseline BLE of 8.5% and satisfying the 5–10% tolerance required for aquaculture growth monitoring. Ablation analysis confirms that both detection enhancements (contributing −1.3% BLE) and tracking optimizations (contributing −2.0% BLE) are necessary to achieve this application-level accuracy.

The polychaeta Neanthes japonica is a common by-product in mariculture ponds. It is rich in essential nutrients, but has not been well-explored. Therefore, this 56-day experiment investigated the effects of substituting N. japonica meal for dietary fishmeal on juvenile tiger puffer (15.49 ± 0.02 g, n = 450 fish). The control diet (CON) contained 40% fishmeal. Freeze-dried N. japonica meal (FNM) was supplemented into CON at the levels of 3% (FNM3), 6% (FNM6), and 9% (FNM9), replacing fishmeal. The fifth diet contained 6% oven-dried N. japonica meal (ONM6), replacing fishmeal. The results indicated that no significant difference was observed in growth, feed efficiency, and somatic index among all the treatment groups. The feed intake of the FNM6 group was significantly higher compared to CON. No significant difference was detected in fish proximate composition, as well as the fatty acid composition, amino acid composition, and muscle texture. The supplementation of N. japonica meal decreased the activities of intestinal lipase and α-amylase. The addition of freeze-dried N. japonica meal significantly up-regulated the expression of the intestinal amino-glycine transporter pat1. It was concluded that adding 9% N. japonica meal to the feed had no significant effect on the growth performance and body composition of juvenile tiger puffer.

This study investigates the effect of gutting on quality characteristics of Urechis unicinctus, stored in ice and at chill temperature (4℃), in terms of sensory assessment, total volatile basic nitrogen, biogenic amines and microbial changes. The gutted and ungutted groups were kept in ice (T1-gutted, T2-ungutted) and at chill (4℃) temperature (T3–gutted, T4-ungutted). The study revealed that gutting worsened the sensory quality (as indicated by hardness, cohesiveness, springiness and chewiness) of all samples and that samples kept at 4°C scored lower than those kept in ice. Total Volatile Basic Nitrogen registered the highest values in gutted samples, exceeding the acceptable limit after 1 day for the T3, and 12 days for T1 samples, respectively. For ungutted samples the threshold value of 30 mg/L has been exceeded after 4 days for T4, and 14 days for T2 samples. In the present study, eight biogenic amines were analyzed; tryptamine and histamine were not detected all the time. The total concentration of biogenic amines in gutted U. unicinctus was significantly higher in comparison with ungutted groups starting from the 8th day, for samples stored in ice, and from the 3rd day for samples kept at 4℃ (p < 0.05). However, the concentration of biogenic amines did not reach the allowable limit, even the samples were unacceptable due to high values of total viable count. Therefore, limits of biogenic amines available for fish are not suitable for U. unicinctus. Sensory scores were significantly correlated with Total Volatile Basic Nitrogen and Total Viable Count in all four groups (p < 0.05). Combined results of this study indicated that shelf life of T1, T2, T3 and T4 were 6, 7, 1 and 4 days, respectively. Gutting had a little effect on the storage of U. unicinctus stored in ice, but obviously shortened the shelf life of samples when stored at 4℃.