Search

Rising scientific literature and legislation measures have highlighted the concern on plastic pollution and the issue of microplastics. In the context of this study, 3 marine species of commercial interest (bogues, Mediterranean mussels, blue crabs) were examined, concerning microplastics’ presence and characteristics. The abundance of the ingested items ranged between 1.22 and 3.30 items/individual. In total, 172 items were extracted from the samples, while only three items were categorised as mesoplastics. The most frequent size for all three species was particles smaller than 200 μm, while fragment was the most frequent type of microplastic (58.48%). In total, 12 colours were recorded, with blue being the most frequent one. Within the sampling areas, significant differences were determined (p

This paper addresses the challenge of reading low contrast text on tyre sidewall images of vehicles in motion. It presents first of its kind, a full scale industrial system which can read tyre codes when installed along driveways such as at gas stations or parking lots with vehicles driving under 10 mph. Tyre circularity is first detected using a circular Hough transform with dynamic radius detection. The detected tyre arches are then unwarped into rectangular patches. A cascade of convolutional neural network (CNN) classifiers is then applied for text recognition. Firstly, a novel proposal generator for the code localization is introduced by integrating convolutional layers producing HOG-like (Histogram of Oriented Gradients) features into a CNN. The proposals are then filtered using a deep network. After the code is localized, character detection and recognition are carried out using two separate deep CNNs. The results (accuracy, repeatability and efficiency) are impressive and show promise for the intended application.

The novelty of this study consists in a multi-modality approach to scene classification, where image and audio complement each other in a process of deep late fusion. The approach is demonstrated on a difficult classification problem, consisting of two synchronised and balanced datasets of 16,000 data objects, encompassing 4.4 hours of video of 8 environments with varying degrees of similarity. We first extract video frames and accompanying audio at one second intervals. The image and the audio datasets are first classified independently, using a fine-tuned VGG16 and an evolutionary optimised deep neural network, with accuracies of 89.27% and 93.72%, respectively. This is followed by late fusion of the two neural networks to enable a higher order function, leading to accuracy of 96.81% in this multi-modality classifier with synchronised video frames and audio clips. The tertiary neural network implemented for late fusion outperforms classical state-of-the-art classifiers by around 3% when the two primary networks are considered as feature generators. We show that situations where a single-modality may be confused by anomalous data points are now corrected through an emerging higher order integration. Prominent examples include a water feature in a city misclassified as a river by the audio classifier alone and a densely crowded street misclassified as a forest by the image classifier alone. Both are examples which are correctly classified by our multi-modality approach., Comment: 6 pages, 10 figures, 3 tables

Reinforcement learning for multi-goal robot manipulation tasks is usually challenging, especially when sparse rewards are provided. It often requires millions of data collected before a stable strategy is learned. Recent algorithms like Hindsight Experience Replay (HER) have accelerated the learning process greatly by replacing the original desired goal with one of the achieved points (substitute goals) alongside the same trajectory. However, the selection of previous experience to learn is naively sampled in HER, in which the trajectory selection and the substitute goal sampling is completely random. In this paper, we discuss an experience prioritization strategy for HER that improves the learning efficiency. We propose the Goal Density-based hindsight experience Prioritization (GDP) method that focuses on utilizing the density distribution of the achieved points and prioritizes achieved points which are rarely seen in the replay buffer. These points are used as substitute goals for HER. In addition, we propose an Prioritization Switching with Ensembling Strategy (PSES) method to switch different experience prioritization algorithms during learning, which allows to select the best performance during each learning stage. We evaluate our method with several OpenAI Gym robotic manipulation tasks. The results show that GDP accelerates the learning process in most tasks and can be improved when combining with other prioritization methods using PSES.

We address and formalise the task of sequence-to-sequence (seq2seq) cross-modal retrieval. Given a sequence of text passages as query, the goal is to retrieve a sequence of images that best describes and aligns with the query. This new task extends the traditional cross-modal retrieval, where each image-text pair is treated independently ignoring broader context. We propose a novel variational recurrent seq2seq (VRSS) retrieval model for this seq2seq task. Unlike most cross-modal methods, we generate an image vector corresponding to the latent topic obtained from combining the text semantics and context. This synthetic image embedding point associated with every text embedding point can then be employed for either image generation or image retrieval as desired. We evaluate the model for the application of stepwise illustration of recipes, where a sequence of relevant images are retrieved to best match the steps described in the text. To this end, we build and release a new Stepwise Recipe dataset for research purposes, containing 10K recipes (sequences of image-text pairs) having a total of 67K image-text pairs. To our knowledge, it is the first publicly available dataset to offer rich semantic descriptions in a focused category such as food or recipes. Our model is shown to outperform several competitive and relevant baselines in the experiments. We also provide qualitative analysis of how semantically meaningful the results produced by our model are through human evaluation and comparison with relevant existing methods.

We introduce rcGAN, a new generative method that is capable of synthesising arbitrary sized, high-resolution images derived from a single reference image used to train our model. Our two-steps method uses a randomly conditioned convolutional generative adversarial network (rcGAN) trained on patches obtained from a reference image. It can capture the reference image internal patches distribution and then produce high-quality samples that share with this image the same visual attributes. After training, the rcGAN generates recursively an arbitrary number of samples which are then stitched together to produce an image whose size is determined by the number of samples that are used to synthesise it. Our proposed method can provide a practically infinite number of variations of a single input image that offers enough variability while preserving the essential large scale constraints. We experiment with our two-steps method on many types of models, including textures, building facades and natural landscapes, comparing very positively against others methods.

The limited quantity of training data can hamper supervised machine learning methods, that generally need large amounts of data to avoid overfitting. Data augmentation has a long history of use with machine learning algorithms and is a straightforward method to overcome overfitting and improve model generalisation. However, data augmentation schemes are typically designed by hand and demand substantial domain knowledge to create suitable data transformations. This paper introduces a GAN based method that automatically learns an augmentation strategy appropriate for sparse datasets and can improve pixel-level semantic segmentation accuracy by filling the gaps in the training set. Our method can also be combined with other augmentation techniques to further improve performance. We evaluate the proposed method's feasibility on four datasets and three semantic segmentation models, leading to improvement in the mean intersection-over-union (mIoU) score of between 0.5 and 14 percentage points, under different circumstances.