Automatic length estimation of free-swimming fish using an underwater 3D range-gated camera

Risholm, Petter; Mohammed, Ahmed; Kirkhus, Trine; Clausen, Sigmund; Vasilyev, Leonid; Folkedal, Ole; Johnsen, Øistein; Haugholt, Karl Henrik; Thielemann, Jens T.

doi:10.1016/j.aquaeng.2022.102227

Cited by 25 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the research, data on the size and positioning detection of relevant binocular products in the air have been included for comparison. 14,34 Similar studies on agricultural products in the air have also been incorporated for comparison. 44,45 The results show that our research achieves high positioning accuracy but only average size detection accuracy.…”

Section: Pose Estimation Experiments With Genetic Algorithm and Diffe...mentioning

confidence: 99%

Expanded photo-model-based stereo vision pose estimation using a shooting distance unknown photo

Tian,

Wang

2024

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Model-based stereo vision pose estimation depends on the establishment of the model. The photo-model-based method simplifies the model-building process with just one photo. Programming languages do not predefine the shapes, colors, and patterns of objects. In the past, however, it was necessary to calculate a pixel per metric ratio, that is, the number of pixels per millimeter of the object, based on the photo’s shooting distance to generate a photo-model with the same size (length and width) as the actual object. It restricts the real application. The proposed method extends the traditional photo-modeling algorithm and relaxes the photo prerequisite for target pose determination. Various pixel per metric ratios will be assumed to generate 3D photo-models of different sizes. These models will then be employed in stereo vision image matching techniques to detect the pose of the target object. Since it is not a data-driven method, it does not require many pictures and pretraining time. This article applies the algorithm to the cleaning of seaports and aquaculture, aiming to locate dead or diseased marine life on the water surface before collection. Pose estimation experiments have been conducted to detect an object’s pose and a prepared photo’s pixel per metric ratio in real application scenarios. The results show that the expanded photo-model stereo vision method can estimate the pose of a target with one pixel per metric ratio unknown photo.

show abstract

Section: Pose Estimation Experiments With Genetic Algorithm and Diffe...mentioning

confidence: 99%

Expanded photo-model-based stereo vision pose estimation using a shooting distance unknown photo

Tian,

Wang

2024

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Calculation of vmin and vmax values uses equation (3) and equation (4). If the vmin and vmax values are out of the range of wavelength values (0 -255) then they will be classified using equation (5). The input values that have been obtained can be used to balance the colors in pixels with equation (6).…”

Section: 21mentioning

confidence: 99%

“…Previous research on fish length estimation was carried out using a 3D camera with a specification of 532 nm solid-state laser with an active Q-switch combined with a fast range-gated black and white CMOS (1280 × 1024) and without de-haze correction [5]. the drawback in previous research is that the image is still in black and white and the resolution is (1280 x 1024) pixels so it can still be improved.…”

Section: Introductionmentioning

confidence: 99%

Fish length estimation of free-swimming grouper in the cage culture using Underwater Televisual System (UTS), De-haze water correction, and deep learning methods

Ahmadi,

Jaya,

Rahmat

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

This study aimed to obtain growth parameters for free-swimming grouper in cage culture by using a stereo camera Underwater Televisual System (UTS) for video recording. The UTS technology, utilizing two cameras, enables 3D perception and triangulation of rays for accurate depth estimation. The collected data underwent de-hazing water correction, preprocessing, and labeling. The length of the grouper was detected using the SSD Mobilenet v3 algorithm, with localization loss of 0.06%, accuracy of 92.00%, precision of 92.00%, recall of 100%, and F1-score of 95.83%. The measured length results indicated averages of 12.65 ± 3.81 cm and 26.00 ± 19.79 cm for two different sizes of free-swimming grouper. The study demonstrated that combining de-hazing water correction with the SSD Mobilenet v3 algorithm allows direct and accurate measurement of free-swimming grouper length. The integration of UTS technology and advanced algorithms significantly enhances the accuracy and efficiency of fish growth measurement in cage culture. These findings have practical implications for the development of sustainable fish farming practices, enabling optimized feed and water management, reduced mortality rates, and maximized production yields. Accurate growth monitoring contributes to the growth of the aquaculture industry, meeting the increasing demand for seafood sustainably.

show abstract

“…This technology can be used to build an automated species-wise fish segregation system to reduce manual labor in separating fishes according to their species [5]. In a practical scenario, the model might need to detect fish species from a large number of fishes captured within a single frame of a camera, and given a limited resolution of a digital camera, some fishes might be constrained to a lower number of pixels making it harder to detect by a deep learning classification model [6]. Therefore, there is a requirement for a method to improve the resolution of these images for the classification model to work better [7].…”

Section: Introductionmentioning

confidence: 99%

Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16

Adhikary¹

2022

Preprint

View full text Add to dashboard Cite

A smart detection and recognition model for the species of a fish from camera footage is of urgent requirement as fishery contributes to a large portion of the world economy and these kinds of advanced models can aid fishermen on a large scale. Such models incorporating a pick-and-place machine can be very useful to sort different fish species in a bulk without human intervention and this can greatly reduce costs for large scale fishing industries. Existing methods for detecting and recognizing fish species have many limitations such as limited scalability, detection accuracy, failing to detect multiple species, degraded performance at a lower resolution, or pinpointing the exact location of the fish. By modifying the head of a very powerful deep learning model namely VGG-16 with pre-trained weights can be used to detect both the species of the fish and find the exact location of the fish in an image by implementing a modified YOLO to incorporate the bounding box regression head. We have proposed the usage of the ESRGAN algorithm along with the proposed neural network to amplify the image resolution by a factor of 4. With this method, the overall detection accuracy of 96.5% has been obtained. The experiment has been conducted based on a total of 9460 images spread across 9 species. After further improving the model, a pick-and-place machine could be integrated for very fast sorting of the fish according to their species in different large-scale fish industries.

show abstract

Automatic length estimation of free-swimming fish using an underwater 3D range-gated camera

Cited by 25 publications

References 26 publications

Expanded photo-model-based stereo vision pose estimation using a shooting distance unknown photo

Expanded photo-model-based stereo vision pose estimation using a shooting distance unknown photo

Fish length estimation of free-swimming grouper in the cage culture using Underwater Televisual System (UTS), De-haze water correction, and deep learning methods

Fish Species Identification on Low Resolution - A Study with Enhanced Super Resolution Generative Adversarial Network (ESRGAN), YOLO and VGG-16

Contact Info

Product

Resources

About