Accurate volume measurement is essential to the marine treasures in aquaculture. However, existing approaches cannot fully meet the growth and evaluation in the volume measurement of sea cucumbers. In this study, the binocular vision was introduced to efficiently and precisely in-situ measure the volume of sea cucumbers. Three modules also included target detection, segmentation, and volume estimation. In the first module, the target detection was used in the variable lighting and environmental conditions under the typical underwater. The reason was that object detection previously failed to monitor underwater environments, due to the fluctuation of light conditions, reflections, and debris in the water. YOLOv8 target detection model was introduced to integrate the multi-head self-attention mechanism, in order to enhance the detection accuracy in these unpredictable conditions. This attention mechanism was significantly improved to detect the sea cucumbers under the complex underwater landscape. A high-precision system was obtained to more effectively process information from different parts of images under these challenging circumstances. In the second module, instance segmentation was used to focus on the precise identification and segmentation of sea cucumber entities. A segmentation model of sea cucumber was constructed using the Segment Anything Model (SAM) with an adapter mechanism. The SAM model was used to more accurately isolate the sea cucumber from its background, even in the presence of noise and other marine organisms in the water. The segmentation was successfully essential for the accuracy of subsequent steps, as the generated mask served as the input for the volume estimation. High-quality mask information was provided to ensure that the shape of the sea cucumber was captured with the necessary details for accurate volume reconstruction. In the third module of volume estimation, the 2D mask maps were input into 3D space to obtain a point cloud representation of sea cucumbers. Poisson surface reconstruction and voxelization were employed to reduce the distortion of the 3D model because point cloud data often suffered from sparsity and noise. Specifically, the sparse data and noise interference were avoided for the accurate 3D model. As such, the actual volume of sea cucumber was faithfully represented for precise measurement. The experimental results demonstrate that the superior performance of the improved detection model was achieved, compared with the existing algorithms. The 92.5% accuracy and a frame rate of 31 frames per second (fps) outperformed the rest, such as Faster RCNN, Cascade RCNN, YOLOv7, and YOLOv8. Additionally, the Poisson surface reconstruction also produced a closer shape approximation of the true sea cucumber, compared with the Alpha Shapes and Ball Pivoting. More accurate volume measurements were better performed at various depths. Specifically, the accuracy of volume measurement reached 94% at a distance of 100 cm, which was 22 percentage points higher than the minimum bounding box and 14 points higher than the Ball Pivoting. Reliable data was then provided to accurately measure the sea cucumber in aquaculture. In conclusion, high efficiency and precision were obtained to measure the sea cucumber volume after 3D reconstruction in underwater conditions. The finding can also offer reliable data to monitor the growth and assess value for more accurate and efficient aquaculture practices.