Automatic Data Collection using In-vehicle Camera Images for Training Machine Learning-based Local Image Feature Matchers

This paper describes a unique and innovative approach that solved the dual problem of starting up a new engineering instructional laboratory in a timely manner, and for teaching engineering students advanced skills in Automatic Data Collection. Students enrolled in a special pilot course were used to develop and startup an Automatic Data Collection laboratory. These students were assigned individual Automatic Data Collection technologies of interest and given total responsibility for the successful startup of the laboratory. The organization and structure of the course modeled the typical team oriented project development efforts in industry. Feedback from students showed the course to be better than a typical lecture/laboratory/demonstration type course in the following ways: 1) students believed they had greater amount of contact with equipment; 2) their experience on the project was more realistic than more traditional courses; 3) they believed they gained a more thorough understanding of the technology under study; and 4) they believed they improved their professional skills making them more marketable to potential employers. With respect to the laboratory itself, startup time was reduced from an estimated 18 months to 14 weeks with the help of the student teams.

A circuit is described for monitoring at the receiving end of an automatic meteorological data collection system, the quality of the data received from remote automatic field terminal station. The received data quality is monitored in terms of the received data for certain prefixed levels of reference voltage transmitted from field. The circuit gives a go-nogo type indication depending on whether or not the reference data levels are received within the prescribed limits and it becomes possible at the data receiving and processing terminal to decide upon the useful part of the incoming data to, be processed and printed out. Additionally the circuit gives the sign of those parameters which can go either positive or negative like temperature. The circuit is elegant yet simple in design and gives trouble free operation.

Implementing electronic identification for performance recording in sheep: II. Cost-benefit analysis in meat and dairy farms

In person re-identification, extracting image features is an important step when retrieving pedestrian images. Most of the current methods only extract global features or local features of pedestrian images. Some inconspicuous details are easily ignored when learning image features, which is not efficient or robust to for scenarios with large differences. In this paper, we propose a Multi-level Feature Fusion model that combines both global features and local features of images through deep learning networks to generate more discriminative pedestrian descriptors. Specifically, we extract local features from different depths of network by the Part-based Multi-level Net to fuse low-to-high level local features of pedestrian images. Global-Local Branches are used to extract the local features and global features at the highest level. The experiments have proved that our deep learning model based on multi-level feature fusion works well in person re-identification. The overall results outperform the state of the art with considerable margins on three widely-used datasets. For instance, we achieve 96% Rank-1 accuracy on the Market-1501 dataset and 76.1% mAP on the DukeMTMC-reID dataset, outperforming the existing works by a large margin (more than 6%).

Considers the growing importance of automatic data collection (ADC) and electronic data interchange (EDI) in logistics and distribution, and the need for an additional paradigm. ADC and EDI require additional conceptual consideration in logistics pedagogy. The utilization of the Internet to acquire knowledge globally is a new and progressive way to advance business logistics. Presents some theoretical hypotheses and procedural guidelines for improved logistical linkages.

Extracting fish size using dual underwater cameras

Existing methods of cross-modality person re-identification usually use set-level global feature constraints to reduce the cross-modality discrepancy. However they often ignore the modality-specific and modality-shared local feature matching. Modality-specific local matching could help extract discriminative identity-consistent features and alleviate spatial misalignment, and modality-shared local matching could make identity-consistent features be correlated in two modalities and mitigate the modality misalignment. Therefore, we establish the intra-modality and inter-modality co-occurrence relation between identity parts. We observe the modality-specific and modality-shared local feature matching of identity parts as intra-modality and inter-modality low-rank relation-finding problems. Therefore, in this work, we propose low-rank local matching (LLM) approach to establish the intra-modality and inter-modality co-occurrence relation between identity parts. First, in order to reinforce identity-consist features in two modalities and correlate these cross-modality identity-consist features together, the local matching (LM) module is designed to estimate partial co-occurrence probability by measuring local feature similarity. Moreover, we propose cross-modality triplet-center loss (CTLoss) which adds global constraint for each class distribution in embedding space to alleviate dramatic data expansion due to modality variance. Extensive experiments on two datasets demonstrate the superior performance of our approach over the existing state-of-the-art. Our code is released on https://github.com/fegnyujian/LLM .

A novel automatic data collection and categorizing (ADCC) technique is proposed, and it captures data based on the content of the acoustic signal. An important problem in automatic acoustic event detection system is to find the start and finish point indexing of acoustic event signal in the recorded signal. Firstly, a pre-profiling-based acoustic signal capturing technique is proposed. In the non-stationary environments (low signal-to-noise ratio), conventional approaches for start and finish indexing detection often fail. It is observed that the accuracy of the automatic event detection technique also degrades. To overcome this problem, secondly, feature extraction is done using Mel Filter Cepstral Coefficient (MFCC). A combined approach for classification is employed using K-means with 1-Nearest Neighbor (1NN). It is expected that ADCC approach integrated with classifier is computationally economical.

Enterprise Architecture (EA) is an approach used to provide decision support based on organization-wide models. The creation of such models is, however, cumbersome as multiple aspects of an organization need to be considered, making manual efforts time-consuming, and error prone. Thus, the EA approach would be significantly more promising if the data used when creating the models could be collected automatically--a topic not yet properly addressed by either academia or industry. This paper proposes network scanning for automatic data collection and uses an existing software tool for generating EA models (ArchiMate is employed as an example) based on the IT infrastructure of enterprises. While some manual effort is required to make the models fully useful to many practical scenarios (e.g., to detail the actual services provided by IT components), empirical results show that the methodology is accurate and (in its default state) require little effort to carry out.

Local image features around interest-points have been widely used in order to exploit the similarities between different views of an object in different images. While there are numerous algorithms on detecting the interest-points and defining the local features, few have focused on the importance of the matching process. In this paper, we presented a method that matches interest-points detected via any algorithm. The method is motivated from human perceptual rules, particularly the Gestalt Psychology, and realizes the fact that “The whole is different from the sum of its parts”. The efficacy of the algorithm is not only the ability to decrease the number of false positive matches but also to increase the number of true positives, yielding rock-steady results for any algorithm based on matching local features.

Understanding the socioeconomic characteristics of passengers is crucial for intelligent services for subway systems. Nevertheless, obtaining such information poses challenges, especially sensitive attributes such as age, due to heightened considerations for data privacy. To address this challenge, we explore the correlation between travel features and age from both macro and micro perspectives and propose an improved Generative Adversarial Network (GAN) for age inference in subway contexts. In the macro level, we extract statistical features from Automatic Fare Collection data and novel features from Points of Interest data. The novel features allow us to examine the relationship between built environment and age. In the micro level, we introduce a comprehensive travel chain, considering the dynamic evolution of passenger trips during multiple days. To address the sample imbalance across age groups, we propose an improved GAN-based framework to infer the age attribute. Our framework incorporates Inner Product to capture interdependency among macro features and employs a Transformer-based module to extract sequential and spatiotemporal features within micro-level travel chains. Finally, the framework is validated using a case study of Guangzhou subway. The results indicate the superiority of our model over baseline approaches like Random Forest, Bayesian Networks, and Variational Autoencoders, showcasing accuracy improvements of 17.75%, 20.29%, and 16.10%, respectively. The use of Inner Product and Transformer-based modules enhances the predictive accuracy of the model. The utilization of travel chains proves to be effective in capturing travel features and improves the model’s accuracy in age inference. Furthermore, we delve into potential applications.

Objective Quality measures in healthcare are crucial for improving outcomes and ensuring patient safety. This study investigated the evolution, implementation, and impact of Primary Care Quality (PCQ). The PCQ aims to facilitate nationwide quality benchmarking, serving as a tool for quality improvement (QI) and research. Design/Settings A descriptive design outlining the development and operationalisation of the PCQ, a national framework for automatic and systematic data collection and feedback. Results The national PCQ system is a tool for continuous QI in primary care in Sweden. PCQ has achieved extensive adoption, with over 97% of Swedish primary care centres, both private and public driven, utilising the platform for automatic data extraction from patient records and data visualisation. Quality indicators were developed through a structured approach involving primary care professionals, evidence-based clinical practices, and expert contributions from established knowledge organisations, reflecting the breadth of general practice. Data are automatically retrieved from medical records and visualised in real time, with the possibility of benchmarking at an aggregate level and identifying individuals locally at primary care centres. The PCQ has facilitated improvements by enabling quality dialogue among healthcare professionals and supporting continuous local QI. Regionally, the PCQ supports needs assessments and patient safety initiatives. Nationally, it establishes standardised indicators for quality measurement, enabling effective benchmarking and strategic healthcare planning. Conclusions The implementation of the national PCQ system provided a framework and tool for continuous QI in primary care. The system has influenced national standardization of primary care indicators, with quality improvement results demonstrated regionally and locally through the PCQ.

During the continual transitions from lab research to real-world applications of vision-based algorithms, there are significant challenges, e.g. the robustness to adapt to complex environments and the high demands of multi-task, multi-modal learning models. More specifically on visual simultaneous localization and mapping (visual SLAM) for mobile robots, two notable limitations are: (i) the drift issue during pose estimation, especially in dynamic environments, makes the positioning system unstable; (ii) the additional loop detection takes many computational resources for image retrieval and global feature geometry checking. This thesis explores the approaches of visual localization on unmanned ground vehicles by solving those limitations. The conventional feature extraction and matching pipeline for vision-based tasks involve three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. The first contribution of the thesis is adding a feature selection and anticipation stage to reduce tracking drift. We explore the noise model of image features to select a subset of all the observed image features with the best ”contribution” during data association and pose estimation across multiple frames. Conventional SLAM algorithms take a strong assumption of scene rigidity, which limits the application under challenging environments. The second part of the thesis addresses the tough issue in dynamic environments with moving objects. We presented GMC, namely the motion clustering approach, a lightweight dynamic object filtering method. It can distinguish moving objects from static landmarks. Based on the theory of motion coherence within a particular image area, GMC could segment dynamic objects in 3D space. We can provide an efficient and robust correspondence algorithm that can extract dynamic objects from a static background with the method. In this way, we propose a dynamic SLAM system that is real-time and free from expensive GPU processors. In contrast to GMC, the thesis’s third part turns to an object-aware learning-based model for more general dynamic scenarios. We use object detection and tracking as points, lines, planes, etc. We utilize semantic information and extract sparse image features simultaneously to keep track of dynamic objects. The static background and different dynamic objects are jointly optimized in a newly developed bundle adjustment sliding window. The estimated 3D bounding boxes can provide more robust camera tracking and better scene understanding, and better map merging. The fourth part of the thesis leverages the emerging feature learning framework. It proposes a unified self-supervised model called LGDNet to generate both global and local image feature descriptors end-to-end. Global feature descriptors embed the whole image into a compact representation, leading to easier scene comparison. On the other hand, local features focus more on the local region similarities of some salient parts for structure from motion. Our proposed method can directly extract features together with descriptors that encode both local maximum responses and global context information, avoiding duplicate calculations based on different feature extraction criteria.

With each passing year, the process of digitalization in society is accelerating, leading to a significant increase in demand for processed and analyzed information. In today's world, data has become a valuable resource, and the ability to quickly find and analyze large amounts of information is a key competitive advantage for companies, researchers, and analysts. In this context, web scraping has become an important tool, enabling the efficient collection of data from various online sources for further analysis and informed decision-making. This paper examines the latest advancements in the development and implementation of effective web scraping methods for automatic data collection and processing using Python. The use of the latest Python libraries, such as BeautifulSoup, Selenium, and Scrapy, allows for high-speed and accurate data collection from various web sources, particularly in secondary markets. The proposed algorithms reduce the risk of site blocking, ensuring the stability and reliability of data collection in various situations. Additionally, the paper places great emphasis on automating the data collection process through the development of automated scripts and the implementation of job scheduling programs, such as cron jobs. This ensures continuous database updates and the collection of new information without manual intervention. Special attention is given to the processing and cleaning of collected data, particularly in the development of methods for filtering out unnecessary information, duplicates, and noise, which enhances data quality. The efficient use of the collected data demonstrates its value for market analysis, demand assessment, and quality forecasting, highlighting the importance of the proposed method. The research includes examples of real-world data use cases in various fields such as marketing, economics, and business analysis. A comparative analysis of different data collection methods is also provided, allowing for the assessment of the effectiveness and reliability of the proposed solutions.

Understanding grassland habitat dynamics in space and time is crucial for evaluating the effectiveness of protection measures and developing sustainable management practices, specifically within the Natura 2000 network and in light of the European Biodiversity Strategy. Land cover maps, derived from remote sensing data, are essential for understanding long-term changes in vegetation cover and land use and assessing the impact of land use changes on grassland ecosystems. In this study, we conducted a 20-year land cover analysis of grassland landscapes in Umbria, Italy, using Random Forest classifications of Landsat data in Google Earth Engine. Our analysis was based on the years 2000, 2010, and 2020. We integrated harmonic modeling, Gray-Level Co-occurrence Matrix (GLCM) textural analysis, statistical image and gradient analysis, and other spectral and Digital Terrain Model (DTM)-derived indices to enhance the classification capabilities. The LandTrendr (LT) algorithm was used in GEE to collect ground control points in no-change areas automatically. We used a method based on Multilayer Perceptron-Artificial Neural Networks (MLP-ANNs) to forecast 2040 land cover. Our land cover classifications and the scenario model validation achieved an overall accuracy of over 90%. However, the classification of shrublands proved challenging due to their mixed composition and unique spatial patterns, resulting in lower accuracies. Feature importance analysis demonstrated the value of the enhanced map composition, and applying the LandTrendr algorithm simplified the diachronic land use and land cover (LULC) classification and change analysis by supporting automatic training data collection. Results support the interpretation of grassland dynamics in Umbria over the past two decades and identify areas affected by encroachment from shrubs, woody plants, or those with reduced green biomass. The forecasting method along with the selection of spatial drivers to predict land cover change, demonstrated high efficiency compared to other studies. A specific analysis was developed to identify areas where conservation measures related to the Natura 2000 network have been more or less effective in preserving grasslands. Overall, the research provides a scientific foundation for a methodology helpful in informing policy decisions and defining spatially explicit management strategies to enhance grassland conservation inside and outside Natura 2000 areas.