A Novel Detection Refinement Technique for Accurate Identification of Nephrops norvegicus Burrows in Underwater Imagery.

With the evolution of the convolutional neural network (CNN), object detection in the underwater environment has gained a lot of attention. However, due to the complex nature of the underwater environment, generic CNN-based object detectors still face challenges in underwater object detection. These challenges include image blurring, texture distortion, color shift, and scale variation, which result in low precision and recall rates. To tackle this challenge, we propose a detection refinement algorithm based on spatial-temporal analysis to improve the performance of generic detectors by suppressing the false positives and recovering the missed detections in underwater videos. In the proposed work, we use state-of-the-art deep neural networks such as Inception, ResNet50, and ResNet101 to automatically classify and detect the Norway lobster Nephrops norvegicus burrows from underwater videos. Nephrops is one of the most important commercial species in Northeast Atlantic waters, and it lives in burrow systems that it builds itself on muddy bottoms. To evaluate the performance of proposed framework, we collected the data from the Gulf of Cadiz. From experiment results, we demonstrate that the proposed framework effectively suppresses false positives and recovers missed detections obtained from generic detectors. The mean average precision (mAP) gained a 10% increase with the proposed refinement technique.

Quantifying ant activity using vibration measurements.

Ant behaviour is of great interest due to their sociality. Ant behaviour is typically observed visually, however there are many circumstances where visual observation is not possible. It may be possible to assess ant behaviour using vibration signals produced by their physical movement. We demonstrate through a series of bioassays with different stimuli that the level of activity of meat ants (Iridomyrmex purpureus) can be quantified using vibrations, corresponding to observations with video. We found that ants exposed to physical shaking produced the highest average vibration amplitudes followed by ants with stones to drag, then ants with neighbours, illuminated ants and ants in darkness. In addition, we devised a novel method based on wavelet decomposition to separate the vibration signal owing to the initial ant behaviour from the substrate response, which will allow signals recorded from different substrates to be compared directly. Our results indicate the potential to use vibration signals to classify some ant behaviours in situations where visual observation could be difficult.