Explore the vast range of titles available.

Humans can quickly approximate how many objects are in a visual image, but no clear consensus has been achieved on the cognitive resources underlying this ability. Previous work has lent support to the notion that mechanisms which explicitly represent the locations of multiple objects in the visual scene within a mental map are critical for both visuo-spatial working memory and enumeration (at least for relatively small numbers of items). Regarding the cognitive underpinnings of large numerosity perception, an issue currently subject to much controversy is why numerosity estimates are often non-veridical (i.e., susceptible to biases from non-numerical quantities). Such biases have been found to be particularly pronounced in individuals with developmental dyscalculia (DD), a learning disability affecting the acquisition of arithmetic skills. Motivated by findings showing that DD individuals are also often impaired in visuo-spatial working memory, we hypothesized that resources supporting this type of working memory, which allow for the simultaneous identification of multiple objects, might also be critical for precise and unbiased perception of larger numerosities. We therefore tested whether loading working memory of healthy adult participants during discrimination of large numerosities would lead to increased interference from non-numerical quantities. Participants performed a numerosity discrimination task on multi-item arrays in which numerical and non-numerical stimulus dimensions varied congruently or incongruently relative to each other, either in isolation or in the context of a concurrent visuo-spatial or verbal working memory task. During performance of the visuo-spatial, but not verbal, working memory task, precision in numerosity discrimination decreased, participants’ choices became strongly biased by item size, and the strength of this bias correlated with measures of arithmetical skills. Moreover, the interference between numerosity and working memory tasks was bidirectional, with number discrimination impacting visuo-spatial (but not verbal) performance. Overall, these results suggest that representing visual numerosity in a way that is unbiased by non-numerical quantities relies on processes which explicitly segregate/identify the locations of multiple objects that are shared with visuo-spatial (but not verbal) working memory. This shared resource may potentially be impaired in DD, explaining the observed co-occurrence of working memory and numerosity discrimination deficits in this clinical population.

Saliency map estimation in computer vision aims to estimate the locations where people gaze in images. Since people tend to look at objects in images, the parameters of the model pre-trained on ImageNet for image classification are useful for the saliency map estimation. However, there is no research on the relationship between the image classification accuracy and the performance of the saliency map estimation. In this study, it is shown that there is a strong correlation between image classification accuracy and saliency map estimation accuracy. The authors also investigated the effective architecture based on multi-scale images and the up-sampling layers to refine the saliency-map resolution. The model achieved the state-of-the-art accuracy on the PASCAL-S, OSIE, and MIT1003 datasets. In the MIT saliency benchmark, the model achieved the best performance in some metrics and competitive results in the other metrics.

In this paper, we present a depth-perceived 3D visual saliency map and propose a no-reference stereoscopic image quality assessment (NR SIQA) algorithm using 3D visual saliency maps and convolutional neural network (CNN). Firstly, the 2D salient region of stereoscopic image is generated, and the depth saliency map is calculated, and then, they are combined to compute 3D visual saliency map by linear weighted method, which can better use depth and disparity information of 3D image. Finally, 3D visual saliency map, together with distorted stereoscopic pairs, is fed into a three-channel CNN to learn human subjective perception. We call proposed depth perception and CNN-based SIQA method DPCNN. The performances of DPCNN are evaluated over the popular LIVE 3D Phase I and LIVE 3D Phase II databases, which demonstrates to be competitive with the state-of-the-art NR SIQA algorithms.

Deep convolutional neural networks (DCNNs) and the ventral visual pathway share vast architectural and functional similarities in visual challenges such as object recognition. Recent insights have demonstrated that both hierarchical cascades can be compared in terms of both exerted behavior and underlying activation. However, these approaches ignore key differences in spatial priorities of information processing. In this proof-of-concept study, we demonstrate a comparison of human observers ( N = 45) and three feedforward DCNNs through eye tracking and saliency maps. The results reveal fundamentally different resolutions in both visualization methods that need to be considered for an insightful comparison. Moreover, we provide evidence that a DCNN with biologically plausible receptive field sizes called vNet reveals higher agreement with human viewing behavior as contrasted with a standard ResNet architecture. We find that image-specific factors such as category, animacy, arousal, and valence have a direct link to the agreement of spatial object recognition priorities in humans and DCNNs, while other measures such as difficulty and general image properties do not. With this approach, we try to open up new perspectives at the intersection of biological and computer vision research.

Inherent in visual scene analysis is a bottleneck associated with the need to sequentially sample locations with foveating eye movements. The concept of a ‘saliency map’ topographically encoding stimulus conspicuity over the visual scene has proven to be an efficient predictor of eye movements. Our work reviews insights into the neurobiological implementation of visual salience computation. We start by summarizing the role that different visual brain areas play in salience computation, whether at the level of feature analysis for bottom-up salience or at the level of goal-directed priority maps for output behaviour. We then delve into how a subcortical structure, the superior colliculus (SC), participates in salience computation. The SC represents a visual saliency map via a centre-surround inhibition mechanism in the superficial layers, which feeds into priority selection mechanisms in the deeper layers, thereby affecting saccadic and microsaccadic eye movements. Lateral interactions in the local SC circuit are particularly important for controlling active populations of neurons. This, in turn, might help explain long-range effects, such as those of peripheral cues on tiny microsaccades. Finally, we show how a combination of in vitro neurophysiology and large-scale computational modelling is able to clarify how salience computation is implemented in the local circuit of the SC. This article is part of the themed issue ‘Auditory and visual scene analysis’.

Vehicle surveillance of a wide area allows us to learn much about the daily activities and traffic information. With the rapid development of remote sensing, satellite video has become an important data source for vehicle detection, which provides a broader field of surveillance. The achieved work generally focuses on aerial video with moderately-sized objects based on feature extraction. However, the moving vehicles in satellite video imagery range from just a few pixels to dozens of pixels and exhibit low contrast with respect to the background, which makes it hard to get available appearance or shape information. In this paper, we look into the problem of moving vehicle detection in satellite imagery. To the best of our knowledge, it is the first time to deal with moving vehicle detection from satellite videos. Our approach consists of two stages: first, through foreground motion segmentation and trajectory accumulation, the scene motion heat map is dynamically built. Following this, a novel saliency based background model which intensifies moving objects is presented to segment the vehicles in the hot regions. Qualitative and quantitative experiments on sequence from a recent Skybox satellite video dataset demonstrates that our approach achieves a high detection rate and low false alarm simultaneously.

Maturity degree and quality evaluation are important for strawberry harvest, trade, and consumption. Deep learning has been an efficient artificial intelligence tool for food and agro-products. Hyperspectral imaging coupled with deep learning was applied to determine the maturity degree and soluble solids content (SSC) of strawberries with four maturity degrees. Hyperspectral image of each strawberry was obtained and preprocessed, and the spectra were extracted from the images. One-dimension residual neural network (1D ResNet) and three-dimension (3D) ResNet were built using 1D spectra and 3D hyperspectral image as inputs for maturity degree evaluation. Good performances were obtained for maturity identification, with the classification accuracy over 84% for both 1D ResNet and 3D ResNet. The corresponding saliency maps showed that the pigments related wavelengths and image regions contributed more to the maturity identification. For SSC determination, 1D ResNet model was also built, with the determination of coefficient ( R 2 ) over 0.55 of the training, validation, and testing sets. The saliency maps of 1D ResNet for the SSC determination were also explored. The overall results showed that deep learning could be used to identify strawberry maturity degree and determine SSC. More efforts were needed to explore the use of 3D deep learning methods for the SSC determination. The close results of 1D ResNet and 3D ResNet for classification indicated that more samples might be used to improve the performances of 3D ResNet. The results in this study would help to develop 1D and 3D deep learning models for fruit quality inspection and other researches using hyperspectral imaging, providing efficient analysis approaches of fruit quality inspection using hyperspectral imaging.

Background Hyperspectral imaging is emerging as a promising approach for plant disease identification. The large and possibly redundant information contained in hyperspectral data cubes makes deep learning based identification of plant diseases a natural fit. Here, we deploy a novel 3D deep convolutional neural network (DCNN) that directly assimilates the hyperspectral data. Furthermore, we interrogate the learnt model to produce physiologically meaningful explanations. We focus on an economically important disease, charcoal rot, which is a soil borne fungal disease that affects the yield of soybean crops worldwide. Results Based on hyperspectral imaging of inoculated and mock-inoculated stem images, our 3D DCNN has a classification accuracy of 95.73% and an infected class F1 score of 0.87. Using the concept of a saliency map, we visualize the most sensitive pixel locations, and show that the spatial regions with visible disease symptoms are overwhelmingly chosen by the model for classification. We also find that the most sensitive wavelengths used by the model for classification are in the near infrared region (NIR), which is also the commonly used spectral range for determining the vegetative health of a plant. Conclusion The use of an explainable deep learning model not only provides high accuracy, but also provides physiological insight into model predictions, thus generating confidence in model predictions. These explained predictions lend themselves for eventual use in precision agriculture and research application using automated phenotyping platforms.

Various rice diseases threaten the growth of rice. It is of great importance to achieve the rapid and accurate detection of rice diseases for precise disease prevention and control. Hyperspectral imaging (HSI) was performed to detect rice leaf diseases in four different varieties of rice. Considering that it costs much time and energy to develop a classifier for each variety of rice, deep transfer learning was firstly introduced to rice disease detection across different rice varieties. Three deep transfer learning methods were adapted for 12 transfer tasks, namely, fine-tuning, deep CORrelation ALignment (CORAL), and deep domain confusion (DDC). A self-designed convolutional neural network (CNN) was set as the basic network of the deep transfer learning methods. Fine-tuning achieved the best transferable performance with an accuracy of over 88% for the test set of the target domain in the majority of transfer tasks. Deep CORAL obtained an accuracy of over 80% in four of all the transfer tasks, which was superior to that of DDC. A multi-task transfer strategy has been explored with good results, indicating the potential of both pair-wise, and multi-task transfers. A saliency map was used for the visualization of the key wavelength range captured by CNN with and without transfer learning. The results indicated that the wavelength range with and without transfer learning was overlapped to some extent. Overall, the results suggested that deep transfer learning methods could perform rice disease detection across different rice varieties. Hyperspectral imaging, in combination with the deep transfer learning method, is a promising possibility for the efficient and cost-saving field detection of rice diseases among different rice varieties.