Image Clues Research Articles

Spatio-temporal fusion with motion masks for the moving small target detection from remote-sensing videos

Moving small target detection is an eye-catching research topic, full of great challenges in object detection field. Its primary difficulties exist in (i) the very small size proportion of the target region in background images, (ii) the quite weak contrast to background and (iii) the perception of slight target motion. Currently-existing detection methods mainly utilize the image features from spatial domain. This kind of features is quite weak to small targets. More new feature kinds need to be concerned. In view of these, besides traditional image clues, motion features are currently attracting more and more attention in small target detection. In order to promote detection performance, this paper proposes a Spatio-Temporal Fusion Network (STFNet) with two parallel feature extraction branches for detecting moving small targets. In this network, one branch is designed to capture the traditional semantic features from spatial domain, and the other is devised to perceive the slight target motion features hidden in temporal domain. Meanwhile, to optimize the extraction of spatio-temporal features, a group of motion masks is specially designed to guide feature extractors to pay more precise attention to the positions where small targets appear. Moreover, we design a new bridging module to enhance the cross-domain and cross-scale fusion of spatio-temporal features. Through extensive comparison and ablation experiments on seven sub-datasets, it is proved that our new STFNet is effective and it is obviously superior to the compared ones in detecting moving small targets from satellite sequence images. It achieves a Precision of 0.93, an mAP50 of 71.10% and an F1 of 0.84, evidently higher than existing state-of-the-art methods. Our codes are available at https://github.com/UESTC-nnLab/STF.

SmokePose: End-to-End Smoke Keypoint Detection

Smoke detection has been a research focus due to its application value in fire and toxic gas leakage alarms. Here we formulate a novel research paradigm for in-depth smoke analysis: modeling the smoke plume in an image with two semantic keypoints, i.e., the start-point (where the smoke comes from) and the end-point (where the smoke spreads), and localizing the keypoints through a heatmap-based detection method. A specialized dataset is developed for smoke keypoint detection, collecting images online and manually annotating the keypoints. Based on the dataset, we propose a Transformer-based model called SmokePose that employs a hierarchical Transformer encoder and a pure Transformer decoder to detect smoke keypoints in an end-to-end manner. We demonstrated the performance of the proposed SmokePose with comparative experiments and ablation studies. A further discussion on the visualization of the attention maps helps to understand the mechanism of SmokePose and to reveal essential image clues for smoke keypoint detection.

Data fusion of multiple machine intelligent systems for the condition assessment of subway structures

Water intrusion through soil is considered the most significant structural issue and the major cause of concrete degradation in subway networks. An enormous amount of water infiltration may expedite the deterioration mechanisms, such as moisture marks, spalling, scaling, and cracks. These mechanisms can compromise the structural durability and jeopardize people’s safety. The condition assessment of concrete infrastructure is predominantly conducted based of visual inspection techniques, which are costly, time-consuming, and error prone. In this research, two main models for the condition assessment of subway networks are proposed. First, image processing techniques and machine intelligent systems are streamlined through successive operations to detect and quantify multiple surface defects automatically. Spatial and frequency domain filters are used to enhance the image clues, in tandem with artificial neural networks (ANNs) and regression analysis (RA) for defect recognition. The Monte Carlo simulation (MCS) is then leveraged to deliver advanced optimization and accurate estimation for each defect’s condition index in the subway element. The developed method was implemented on four stations in Montréal subway systems, whereby the performance of ANNs and RA was validated through R2 as 0.928 and 0.957, respectively. Moreover, the MCS forecast precision was recorded as 95% percentile, which proves the efficacy of the developed models. This research provides insights for infrastructure managers about maintenance and intervention plans in order to prioritize their spending policies.

Analysis of Community Interaction Modules of European and American Universities

Purpose—Using a sample of universities from Europe and North America the research herein seeks to understand the content trends of university brand pages through an exploration of the social community and the measurement of user participation and behavior. The analysis relies on an artificial intelligence approach. Through the verification of interactions between users and content on the university brand pages, recommendations are made, which aim to ensure the pages meet the needs of users in the future. Design/methodology/approach—The study sample was drawn from six well-known universities in Europe and North America. The content of 23,158 posts made over the course of nine years between 1 January 2011 to 31 December 2019 was obtained by a web crawler. Concepts in the fields of computer science, data mining, big data and ensemble learning (Random Decision Forests, eXtreme Gradient Boosting and AdaBoost) were combined to analyze the results obtained from social media exploration. Findings—By exploring community content and using artificial intelligence analysis, the research identified key information on the university brand pages that significantly affected the cognition and behavior of users. The results suggest that distinct levels of user participation arise from the use of different key messages on the university fan page. The interactive characteristics identified within the study sample were classified as one of the following module-types: (a) information and entertainment satisfaction module, (b) compound identity verification module or (c) compound interactive satisfaction module. Research limitations/implications—The study makes a contribution to the literature by developing a university community information interaction model, which explains different user behaviors, and by examining the impact of common key (image) clues contained within community information. This work also confirms that the behavioral involvement of users on the university’s brand page is closely related to the information present within the university community. A limitation of the study was the restriction of the sample to only European and North American cultural and economic backgrounds and the use of Facebook as the sole source of information about the university community. Practical implications—Practically, the research contributes to our understanding of how, in official community interactions, user interactions can be directed by features such as information stimuli and brand meanings. In addition, the work clarifies the relationship between information and user needs, explaining how the information characteristics and interaction rules particular to a given school can be strengthened in order to better manage the university brand page and increase both the attention and interaction of page users. Originality/value—This research provides an important explanation of the role of key information on the university fan pages and verifies the importance of establishing key (image) clues in the brand community, which in turn affect user cognition and interaction. Although related research exists on information manipulation and the importance of online communities, few studies have directly discussed the influence of key information on the fan pages of university brands. Therefore, this research will help to fill gaps in the literature and practice by examining a specific context, while at the same time providing a valuable and specific reference for the community operation and management of other related university brands.

Research on the Impact of Clue Consistency on Purchasing Decisions of Peer-to-Peer Accommodation Platform: Interaction between Text and Image Clues

Research on the Impact of Clue Consistency on Purchasing Decisions of Peer-to-Peer Accommodation Platform: Interaction between Text and Image Clues

DeepNEM: Deep Network Energy-Minimization for Agricultural Field Segmentation

One of the main characteristics of agricultural fields is that the appearance of different crops and their growth status, in an aerial image, is varied, and has a wide range of radiometric values and high level of variability. The extraction of these fields and their monitoring are activities that require a high level of human intervention. In this article, we propose a novel automatic algorithm, named deep network energy-minimization (DeepNEM), to extract agricultural fields in aerial images. The model-guided process selects the most relevant image clues extracted by a deep network, completes them and finally generates regions that represent the agricultural fields under a minimization scheme. DeepNEM has been tested over a broad range of fields in terms of size, shape, and content. Different measures were used to compare the DeepNEM with other methods, and to prove that it represents an improved approach to achieve a high-quality segmentation of agricultural fields. Furthermore, this article also presents a new public dataset composed of 1200 images with their parcels boundaries annotations.

The Craving and Excitement of Social Networking Sites Addicts: Based on Cue-Reactivity.

Everyone benefits from social networking as a daily tool, but there are potential addictions. However, little is known about the craving and excitability of social networking sites addiction, and mode of change in psychological craving. The study consisted of two experiments that used a cue-reactivity paradigm to study the cravings and excitement of social networking sites (SNSs) addiction and the changing regulars in cravings. Sixty subjects were divided into a high-score group and a low-score group. In Experiment 1, all subjects evaluated word clues. The results showed that the SNS-related clues only induced the craving and excitability of the high-score group, but not the low-score group, and the craving fluctuated. Furthermore, in Experiment 2, image clues were used. The results showed that the craving induced by an image clue is significantly higher than the craving induced by a word clue, and there is no difference in excitability. Taken together, our findings suggest the SNS-related stimulation, especially image clues, could significantly induce subjects for the craving and excitability of social networks, and the craving fluctuates.

Segmentation of female pelvic cavity in axial T2-weighted MR images towards the 3D reconstruction.

The anatomies of pelvic structures are critical for the diagnosis of pelvic floor dysfunctions. However, because of the complex background, the imaging appearances of pelvic organs and muscles are frequently distorted by noise and partial volume effect. Magnetic resonance imaging with its clear imaging quality of the female pelvic cavity is preferred for many studies. As such, correct segmentations of the pelvic structures on MR images are required for accurate diagnoses. Effective algorithms for axial T2-weighted MR images have been proposed, which are based on the imaging features of different structures and various image clues. In this paper, we review these algorithms and evaluate their performance, and discuss implementation issues and aspects towards constructing the three-dimensional models.

AUSTRALIA'S DESTINATION IMAGE AMONG MAINLAND CHINESE TRAVELERS: AN EXPLORATORY STUDY

This study employed a multi‐faceted image assessment (MIA) framework in exploring Australia's destination image among mainland Chinese travelers. In addition to cognitive and affective image features, multi‐sensory image features were also examined. Data were collected in Beijing using focus groups comprising both past visitors and nonvisitors to Australia. No significant differences were found between the past visitor and non‐visitor groups with regard to cognitive and affective image features. However, past visitors seemed to hold more multi‐sensory image clues than their non‐visitor counterparts based on previous visit experiences. Salient cognitive image features identified included kangaroos and koalas, Australia's natural environment, iconic attractions like the Sydney Opera House, the Great Barrier Reef, and the Sydney Harbour Bridge, vastness of the land, comfortable living conditions, and lack of cultural atmosphere and historical heritage. Affectively, participants viewed Australia as a “relaxing” holiday destination. Marketing implications were discussed based on the study findings.

Maximum entropy model-based baseball highlight detection and classification

In this paper, we propose a novel system that is able to automatically detect and classify baseball highlights by seamlessly integrating image, audio, and speech clues using a unique framework based on maximum entropy model (MEM). What distinguishes our system is that we emphasize on the integration of multimedia features and the acquisition of domain knowledge through automatic machine learning processes. Our MEM-based framework provides a simple platform capable of integrating multimedia features as well as their contextual information in a uniform fashion. Unlike the Hidden Markov Model and the Bayes Network-based approaches, this framework does not need to explicitly segment and classify the input video into states during its data modeling process, and hence remarkably simplifies the training data creation and the highlight detection/classification tasks. Experimental evaluations demonstrate the superiority of our proposed baseball highlight detection system in its capability of detecting more major baseball highlights, and in its overall accuracy of detecting these major highlights.