Computer Vision Based Planogram Compliance Evaluation

LSMCL: Long-term Static Mapping and Cloning Localization for autonomous robot navigation using 3D LiDAR in dynamic environments

With the continuous advancement of deep learning, object detection has made remarkable progress in accurately identifying a wide range of object categories, even within increasingly complex scenes. However, as the number of categories grows, visual concepts naturally organize into a label hierarchy. We contend that existing hierarchical classification and detection methods predominantly prioritize fine-grained prediction, potentially leading to inconsistencies with realistic human perception. From this perspective, we investigate the Hierarchical Object Detection (HOD) problem to better align with real-world perception. To address the lack of benchmarks in the field, we build a large-scale HOD benchmark termed RHOD with open-source datasets, comprising 740 categories. To better align the hierarchical object detectors towards realistic perception, we propose a new evaluation metric named Hierarchical Average Precision (HAP). Furthermore, we present a novel hierarchical object detection method that includes two components, Tree Soft Labeling (TSL) and Hierarchical Extension and Suppression (HES). Our method mitigates the issue of overconfidence in fine-grained predictions, which has been prevalent in previous approaches. We evaluate a range of existing methods on the RHOD benchmark, including plain, hierarchical, and open-vocabulary models. Additionally, we perform comprehensive experiments to assess the performance of our proposed method. The experimental results show that our method achieves state-of-the-art performance on the RHOD benchmark.

Membrane distillation driven by intermittent and variable-temperature waste heat: System arrangements for water production and heat storage

Subject area Strategic management, HR Management, Change management, Marketing. Study level/applicability Potential audience. This case will serve to undergraduate students, master level students, in the subjects, entrepreneurship, managing change, marketing, H&R management, strategic management. Case overview The Brunes Company was founded in 1994 by Gerond Cela and his brother, with the goal to provide quality products for bathrooms in the then-emerging Albanian market. During the next few years, it had grown into one of the biggest wholesale and retail chains in Albania, with huge portfolio of goods for home refurbishing. The beginnings were very humble. Armed only with the high school diploma in textile trading, born and raised in an ex-communist country without developed entrepreneurship culture, Gerond set off to Italy, a popular destination for young Albanians who were looking for an opportunity to escape the pitfalls of the post-communist transitional economy. Gerond recognized the huge gap in the market for imported tiles in his home country, so he began importing quality Italian tiles in 1994. Initially, he was doing the wholesale from his truck, due to the lack of retail stores. He focused on increasing customer satisfaction and built the company name as trustful provider of quality goods. This strategy brought him less profit, but his long-term goal was to build the company name and to establish it as a trustful provider of quality goods. In 1999, he bought 18,000 m2 (for 50.000 euro) land on the highway Tirana-Durres, 7 km from the city centre, which proved to be extremely worthwhile in the long run because the price of the land had skyrocketed up to ten times during the next decade, due to the economic development of Albania. In 2004, Gerond and his brother epitomized their business idea. They entered the market of home furniture. In 2009, the company expanded further in country towns like Lezha, Saranda and Fier. After two decades of establishing his company as a market leader with approximately 30 per cent of market share, Brunes Company is at the crossroads. On one hand, it is pressured by very stiff competition in the form of their main competitor Delta Home, which succeeded in taking 10-15 per cent of the marketing just in one year. On the other hand, the company has been stagnating for some period without a concrete plan to overcome this problem, as well as without a clear strategy for the future directions of the expansion. To diversify the company’s portfolio, Gerond built a factory for tiling accessories which will cost 8 million Euros and employs about 30 workers. Expected learning outcomes Specific objectives of the case are as follows: to portray individuals who became successful primary through their leadership abilities, and to examine how their experiences and values contributed to the success of their business; illustrate the impact on operations of an increasingly competitive environment and how this environment affects the need for a change in strategy; identify the challenges of selling luxury goods in a competitive retail environment; to assist students to critically think about diversification strategy; to gain an understanding how to adapt to change; to discuss for issues that must be changed (culture, people, technology, values and philosophy of leadership, marketing, business model), to grow. Supplementary materials Teaching notes are available for educators only. Please contact your library to gain login details or email support@emeraldinsight.com to request teaching notes. Subject code CSS 11: Strategy

This study addresses operational inefficiencies in small-scale laundry services by implementing a tailored web-based information system. Many businesses face challenges in managing transactions, tracking orders, and reducing errors due to reliance on manual processes. The research aims to optimize service delivery and enhance customer satisfaction through digital transformation. Using a mixed-methods approach, data were collected through interviews and workflow observations. The system was developed following the Waterfall model, utilizing HTML, CSS, JavaScript, and MySQL. Iterative testing ensured the system’s functionality and user-friendliness. Results showed a 70% reduction in transaction processing time and a 90% decrease in manual errors. Improved order tracking also increased customer satisfaction. The study’s novelty lies in its tailored, scalable solution for micro-enterprises, setting the stage for further innovations like AI-driven analytics to support growth.

This article examines how consumers evaluate retailer rebranding strategies, with a specific focus on the rebranding of “Promogro” to “MG Maxi” in Tunisia. The study addresses the need to understand consumer reactions to brand transitions, particularly in a competitive retail market. A quantitative research approach was employed, utilizing survey data collected from a sample of 351 Tunisian consumers, which was analyzed using structural equation modelling (SEM) to test the main hypotheses and assess the impact of key variables on consumer evaluation. The findings reveal a negative correlation between customers’ attachment to the old retailer brand and their attitudes toward the rebranding process. Furthermore, retailer brand perceptions act as a competitive mediator between attitudes toward rebranding and consumers’ intentions to revisit. The results also indicate that the perceived similarity of the new retailer brand positively moderates the relationship between consumer attachment and perceptions of the renovated retailer brand. Specifically, strong attachment to the old brand leads to more favorable perceptions of the new brand when similarity is high. This study provides insights for practitioners on key success factors for consumer acceptance during rebranding, offering practical guidance for a seamless transition in the Tunisian market.

Bronchoscopists rely on navigation systems during bronchoscopy to reduce the risk of getting lost in the complex bronchial tree-like structure and the homogeneous bronchus lumens. We propose a patient-specific branching level estimation method for bronchoscopic navigation because it is vital to identify the branches being examined in the bronchus tree during examination. We estimate the branching level by integrating the changes in the number of bronchial orifices and the camera motions among the frames. We extract the bronchial orifice regions from a depth image, which is generated using a cycle generative adversarial network (CycleGAN) from real bronchoscopic images. We calculate the number of orifice regions using the vertical and horizontal projection profiles of the depth images and obtain the camera-moving direction using the feature point-based camera motion estimation. The changes in the number of bronchial orifices are combined with the camera-moving direction to estimate the branching level. We used three in vivo and one phantom case to train the CycleGAN model and four in vivo cases to validate the proposed method. We manually created the ground truth of the branching level. The experimental results showed that the proposed method can estimate the branching level with an average accuracy of 87.6%. The processing time per frame was about 61 ms. Experimental results show that it is feasible to estimate the branching level using the number of bronchial orifices and camera-motion estimation from real bronchoscopic images.

This paper introduces a priority based edge detection of license plate and recognition of characters. We intend to extract and identify vehicle registration numbers from real time vehicle images without any human intrusion. In computation of license plate, localization shows better edge detection result when compared to conventional methods such as binarization, template matching or transition mapping. Although several effective image processing algorithms are created nowadays, real time operation is found to be impractical as their application is limited by huge computation requirements. As processing time and illumination of the image affects real time operation, it is reduced by setting a dynamic threshold. This paper uses the concept of localization for license plate extraction from real time images followed by the segmentation of characters and reformation.

Artificial vision in robotics involves real time detection of objects for fast decision making. Such intelligent systems require efficient algorithms and big learning database of examples for producing robust classifiers. Several methods of objects detection and tracking have been proposed in the literature. However, even though the detection rates have been improved, the processing time and the complexity of the models still representing a key challenge. In this paper, we present a real time object detection and tracking framework based on Adaboost classification, where a strong classifier is generated using an iterative combination of weak learners. This method is based on the use of discriminative features by analyzing different regions of the input image. Instead of performing a full traversal in the entire search space of all possible visual features, we propose to use intelligent heuristics for accelerating time processing and extracting relevant features in the image that lead to a best detection rate. The meta-heuristics involve the use of genetic algorithms, particle swarm optimization, random walk and a novel hybrid combination of these methods. The obtained results, in a case of intelligent transportation system, have shown considerable improvements in term of computation time, efficiency and accuracy.

Logo detection in images is particularly challenging due to limited access to well-labelled data. Many existing logo detection methods are not scalable to larger datasets due to tedious bounding-box annotation work. As a result, with only a small number of logo classes and limited well-labelled images per class, their performance deteriorates on real-world applications. In this work, we propose a data augmentation and training pipeline to tackle these challenges. Specifically, we develop an incremental learning approach that starts training using synthetic data, followed by iteratively obtaining real training images from a given source and updating the current model with the newlyobtained data. To avoid model drift, we add a human curation step where incorrect detections (false-positives) are filtered out by simple-clicks using a User Interface, we designed. With this approach, we were able to generate a large (173,000 images of 173 logo classes) dataset termed Logo173 where all images are annotated with bounding-boxes. This image dataset can also be used to train a frame-by-frame baseline logo detector for videos. We demonstrate with extensive experiments that the proposed pipeline significantly saves time and effort for tedious data annotation and outperforms a current state-of-the-art logo detection method.

Fault diagnosis for Autonomous underwater Vehicle (AUVs) is a key technology for ensuring the safety of AUVs and an important skill for enabling them to autonomously perform tasks underwater for long periods. The effectiveness of current diagnostic methods is affected by the reliability of expert knowledge and the accuracy of model establishment. In addition, some data-driven diagnostic methods lack robustness. Unlike traditional model-based fault diagnosis methods, this paper proposes a fault diagnosis method for AUVs based on the LSTM (Long Short-Term Memory) algorithm. LSTM is good at processing time series data and can learn complex temporal patterns. Therefore, the LSTM model is used to learn the mapping of state data to its corresponding fault types. The underwater environment in which AUVs work is complex and ever-changing, and packet loss may occur during data transmission, resulting in partial loss of online data. To address this issue, this paper fills in missing values during the feature processing stage and then uses a BiLSTM-Attention-MiniLoss algorithm to enhance the robustness of the diagnostic model. Finally, the fault diagnosis accuracy of the original LSTM and the BiLSTM-Attention-MiniLoss was compared based on an open-source dataset under different degrees of data loss. The experimental results showed that the fault diagnosis methods for AUV based on LSTM and the BiLSTM-Attention-MiniLoss could predict the type of fault based on the navigation status data of the AUV, with BiLSTM-Attention-MiniLoss performing better.

This study aims to determine the influence of Store Atmosphere and Product Quality on Purchasing Decisions among consumers of Setia Budi Street Pure Milk, Medan. This study used a quantitative approach with multiple linear regression analysis. The sample size was 90 respondents obtained through accidental sampling. Data collection was conducted through questionnaires.Partial test results indicate that Store Atmosphere has a positive and significant effect on Purchasing Decisions, with a calculated t-value of 6.420 > t-table 1.986 and a significance value of 0.000 < 0.05. Product Quality also has a positive and significant effect on Purchasing Decisions, with a calculated t-value of 4.270 > t-table 1.986 and a significance value of 0.000 < 0.05. The simultaneous test results indicate that Store Atmosphere and Product Quality jointly have a significant effect on Purchase Decisions, with a calculated F-value of 121.444 > F-table of 3.100 and a significance value of 0.000 < 0.05. The Adjusted R-square value of 0.721 indicates that 72.1% of the variation in Purchase Decisions can be explained by these two independent variables, while the remaining 27.9% is explained by other factors not examined in this study.Therefore, it can be concluded that a comfortable store atmosphere and good product quality play a significant role in driving consumer purchasing decisions. These findings can provide a strategic basis for businesses to increase customer satisfaction and loyalty.

The purpose of th article is to substantiate the possibility of applying methods for assessing the effectiveness and risks of investing for the analysis of income in the strategic management of real property. Methodology. The methodical bases of sensitivity analysis and simulation modeling of cash flows of real property income are stated. Results. The critical factors of costs and revenues affecting net present value of total cash flow from grain elevator real property object have been revealed. It is evidenced that the most significant factors influencing the amount of cash flows are the volume of sales of grain elevator services, to a lesser extent the total costs and the lack of sensitivity of net present value to staff salary variations. Simulation modeling of the change in net present value due to the change of the most significant uncertain factors was performed, which confirmed the assumptions about the efficiency of the investigated real property. The key factors are the main services that generate net operating income and critical expenses. Namely, services: storage, drying, shipment by road and rail, costs: fuel for drying, electricity, fuel for transportation of grain, staff salaries. For each factor, the relevant limits of change were established (determined by experts taking into account the average annual growth rate of the indicator) and cash flow simulation was performed. Practical implications. Statistical analysis of the model's behavior under the influence of random factors shows that the most probable value of the net present value of cash flows will be positive, despite the simulation of a significant change (+/- 40%) in electricity and fuel consumption factors for grain transportation. The values of the simple and discounted payback period also confirm the efficiency of the elevator property functioning. The indicator of the stability level demonstrate the need of planning input cash flows sources to cover the output cash flows. Value/originality. The expected profitability of grain elevator real property is largely determined by the factor of the volume of basic services sales (storage, drying, shipment and transport of products). This creates the preconditions for the subsequent assessment of the value of grain elevator real property based on the methodology of the income approach.

최근 위치 정보의 이용이 여러 분야에 걸쳐 급격하게 증가하고 있다. 실외에서는 위치 정보의 획득을 위해 일반적으로 GPS 기술을 사용하였으나, 복잡한 실내 공간에서는 벽, 기둥과 같은 물리적인 장애물들로 인해 발생한 다중경로 간섭으로 무선 근거리통신망, RFID, 블루투스 등의 무선 네트워크 기술을 적용한 연구가 진행되었다. 그러나 이러한 위치 측정 기술들은 센싱 인프라스트럭쳐 구축비용이 많이 들며, 측위에 있어 계산 집약적이고, 실내 구조에 따른 정확도의 변화가 발생하는 한계가 존재한다. 본 연구에서는 이러한 한계점을 보완하고자 복합용도건물 내에서 쉽게 획득 및 식별이 가능한 상가, 컨벤션 센터 및 오피스의 전화번호, 방 번호, 상호명과 같은 서술 데이터를 이용하여 위치를 추출한다. 이 과정에서 문자 매칭을 활용하며, 위치 추정에 있어 신속한 계산과 실내 환경에 따른 정확도 변화를 배제하기 위해 지오코딩 방법을 적용한다. 본 연구에서 제안된 방법을 아키텍쳐로 설계하며, 구현을 위해 3차원 가시화 프로그램을 개발한다. 또한 제한된 기법에서의 매칭률, 프로세싱 시간을 통하여 정략적으로 평가한다. Recently, the use of locational information is growing rapidly. GPS technology has been adopted generally for obtaining locational information in outdoor spaces. In the other hand, the researches on indoor positioning have been carried out applying WLAN, RFID or Bluetooth technology because of the multi-path interference of GPS signal caused by the physical obstacles such as walls or columns in buildings. However, such technologies for indoor positioning cost too much to build sensing infrastructure and compute-intensive processes are involved. Furthermore, the accuracy of location estimation is variable caused by interior structures in buildings. In this study, to make up for the limitations, descriptive data such as phone number, unique room numbers, or business names readily available in mixed-use buildings is used for extracting location information. Furthermore, during the process, a geocoding method using character matching is applied to this study enabling prompt location estimation and sublating the fluctuation of accuracy caused by interior structures. Based on the proposed method in this study, an architecture is designed, and three-dimensional viewer program is developed for the implementation of this study. Also, this research is quantitatively analyzed through match rate and processing time of proposed method.

In the recent pandemic, accurate and rapid testing of patients remained a critical task in the diagnosis and control of COVID-19 disease spread in the healthcare industry. Because of the sudden increase in cases, most countries have faced scarcity and a low rate of testing. Chest X-rays have been shown in the literature to be a potential source of testing for COVID-19 patients, but manually checking X-ray reports is time-consuming and error-prone. Considering these limitations and the advancements in data science, we proposed a Vision Transformer-based deep learning pipeline for COVID-19 detection from chest X-ray-based imaging. Due to the lack of large data sets, we collected data from three open-source data sets of chest X-ray images and aggregated them to form a 30 K image data set, which is the largest publicly available collection of chest X-ray images in this domain to our knowledge. Our proposed transformer model effectively differentiates COVID-19 from normal chest X-rays with an accuracy of 98% along with an AUC score of 99% in the binary classification task. It distinguishes COVID-19, normal, and pneumonia patient’s X-rays with an accuracy of 92% and AUC score of 98% in the Multi-class classification task. For evaluation on our data set, we fine-tuned some of the widely used models in literature, namely, EfficientNetB0, InceptionV3, Resnet50, MobileNetV3, Xception, and DenseNet-121, as baselines. Our proposed transformer model outperformed them in terms of all metrics. In addition, a Grad-CAM based visualization is created which makes our approach interpretable by radiologists and can be used to monitor the progression of the disease in the affected lungs, assisting healthcare.