Object detection for crabs in top-view seabed imagery

TL;DR

This paper explores applying an end-to-end neural network combining convolutional and LSTM layers for object detection in underwater, aerial, and standard datasets, aiming to improve marine species identification.

Contribution

It introduces a novel neural network architecture integrating convolutional and LSTM layers for diverse object detection tasks in marine imagery.

Findings

Effective detection of crabs, sea lions, and Pascal VOC objects

Demonstrated versatility across underwater and aerial images

Potential for improved marine species monitoring

Abstract

This report presents the application of object detection on a database of underwater images of different species of crabs, as well as aerial images of sea lions and finally the Pascal VOC dataset. The model is an end-to-end object detection neural network based on a convolutional network base and a Long Short-Term Memory detector.