International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 10 | Oct 2025
p-ISSN: 2395-0072
www.irjet.net
3D Markerless Tracking of a Single Fish: A Clean-Water Baseline and First Aged-Water Comparison Artham Gupta ---------------------------------------------------------------------------***-------------------------------------------------------------------------analysis could benefit aquaculture by allowing quick interAbstract Most studies of fish behavior rely on single-view 2D tracking, which obscures depth and biases motion metrics. I built a simple 3D pipeline using two orthogonal cameras (front and side) and OpenCV-based markerless centroid tracking to reconstruct per-frame (X, Y, Z) positions of a single fish. From the fused trajectory I computed 3D speed, rolling mean speed, speed autocorrelation, 3D voxel occupancy (3×3×3), normalized spatial entropy, and path tortuosity (straightness index and turning-angle statistics). In a clean-water baseline the fish showed broad occupancy (entropy = 0.936 on a 0–1 scale) and a right-skewed speed distribution (mean = 1157 px/s; median = 273 px/s). A first comparison in aged water (same fish, same setup) showed higher central tendency of speed (median = 696 px/s; +155%) but lower spatial entropy (0.698; −25%), suggesting steadier cruising within a reduced spatial envelope. Turning-angle histograms indicated more 60–90° reorientations and fewer extreme U-turns in aged water; straightness index remained low in both conditions. These are pilot results (n = 1 per condition, pixel units), but the code and parameters are transparent and reproducible. The pipeline supports future multi-session statistics, calibration to cm/s, and hypothesis tests on speed, occupancy, entropy, tortuosity, and autocorrelation. Key Words: fish behavior, water quality, 3D tracking, OpenCV, two-view fusion, entropy, tortuosity
1. INTRODUCTION Fish are often used as bio-indicators of aquatic environmental conditions due to noticeable changes in their movement patterns and activity levels with changes in water quality [1][2]. For example, the depletion of dissolved oxygen or the buildup of common pollutants such as ammonia can lead to observable shifts in how fish swim, feed, or the areas of the tank within which they spend their time [3][4]. Therefore, researchers have found an accurate link between fish behavior and real-time water quality. Specifically, a reduction in overall activity and feeding, or displays of stressful behavior in poor water conditions make fish natural "monitors" of water quality [4][5]. This is significant because early detection of suboptimal water conditions through motion and behavior
© 2025, IRJET
|
Impact Factor value: 8.315
|
vention [1][6].
For this research's purpose we define clean water as dechlorinated tap water with TDS levels under 300, whereas aged water refers to originally clean water which has degraded in quality through natural accumulation of metabolic waste products (like ammonia or nitrite) over time. Although aged, cycled water contains beneficial bacteria, it may have lower dissolved oxygen levels and higher waste that stresses fish if not well-maintained [7]. We clarify that in this study "aged" water has been in a tank through one full cycle and contains natural wastes to safe levels, as confirmed through frequent multi-faceted water quality tests. Existing literature emphasizes that even minor alterations in the quality of water can affect the behavior of fish. Most studies focus on extreme cases that show high pollution or poor water conditions can cause fish to be lethargic, feed less, and even avoid certain areas [6]. For example, elevated ammonia concentrations can damage fish gills, increase lethargy, and reduce feeding activity [3][4]. Moreover, increased turbidity (cloudiness) of water due to suspended particles can impair visual sensing in fish, which can further contribute towards increasing foraging time and reducing feeding success rates [8][9]. Additionally, even low to moderate turbidity in aquariums has shown to change school patterns and predatory escape since fish rely heavily on vision to coordinate and avoid threat [10], with one study showing that turbidity above ~9 NTU significantly decreased the prey capture success of dace and significantly affected energy expenditure while feeding [8]. While this is true for many species, some can tolerate moderate levels of turbidity without an immediate breakdown in behavior. For example, stickleback shoals have been observed to remain cohesive in their groups even under certain turbid conditions [11], which indicates that the effect of turbidity can vary by species and context. Overall, however, most literature suggests that small fish are particularly sensitive to water quality, and exhibit reduced activity as well as altered spatial preference under poor water conditions [6]. While most studies have focused on extreme pollutants, there is a relative knowledge gap in studies of how an individual small fish's behavior changes due to moderate alterations of water quality, which are more realistic for artificial aquariums [6].
ISO 9001:2008 Certified Journal
|
Page 806