Urban environments are evolving rapidly in big cities; keeping track of these changes is becoming harder. Information regarding urban features, such as the number of trees, lights, or shops in a particular region, can be crucial for tasks, such as urban planning, commercial campaigns, or inferring various social indicators. StreetScouting is a platform that aims to automate the process of detecting, visualizing, and exporting the urban features of a particular region. Recently, the advent of deep learning has revolutionized the way many computer vision tasks are tackled. In this work, we present StreetScouting, an extensible platform for the automatic detection of particular urban features of interest. StreetScouting utilizes several state-of-the-art computer vision approaches including Cascade R-CNN and RetinaFace architectures for object detection, the ByteTrack method for object tracking, DNET architecture for depth estimation, and DeepLabv3+ architecture for semantic segmentation. As a result, the platform is able to detect and geotag urban features from visual data. The extracted information can be utilized by many commercial or public organizations, eliminating the need for manual inspection.

The vast volume of media content, combined with the costs of manual annotation, challenges scalable codebook analysis and risks reducing decision-making accuracy. This study evaluates the effectiveness of large language models (LLMs) and multi-agent teams in structured media content analysis based on codebook-driven annotation. We construct a dataset of 200 news articles on U.S. tariff policies, manually annotated using a 26-question codebook encompassing 122 distinct codes, to establish a rigorous ground truth. Seven state-of-the-art LLMs, spanning low- to high-capacity tiers, are assessed under a unified zero-shot prompting framework incorporating role-based instructions and schema-constrained outputs. Experimental results show weighted global F1-scores between 0.636 and 0.822, with Claude-3-7-Sonnet achieving the highest direct-prompt performance. To examine the potential of agentic orchestration, we propose and develop a multi-agent system using Meta’s Llama 4 Maverick, incorporating expert role profiling, shared memory, and coordinated planning. This architecture improves the overall F1-score over the direct prompting baseline from 0.757 to 0.805 and demonstrates consistent gains across binary, categorical, and multi-label tasks, approaching commercial-level accuracy while maintaining a favorable cost–performance profile. These findings highlight the viability of LLMs, both in direct and agentic configurations, for automating structured content analysis.

The recent advancements in the field of deep learning have fundamentally altered the manner in which certain challenges and problems are addressed. One area that stands to greatly benefit from such innovations is the realm of urban planning, where the utilization of these tools can facilitate the automatic detection of landscape objects in a given area. However, it must be noted that these data-driven methodologies necessitate significant amounts of training data to attain desired results. This challenge can be mitigated through the application of transfer learning techniques, which reduce the amount of required data and permit the customization of these models through fine-tuning. The present study presents street-level imagery, which can be utilized for fine-tuning and deployment of custom object detectors in urban environments. The dataset comprises 763 images, each accompanied by bounding box annotations for five landscape object classes, including trees, waste bins, recycling bins, shop storefronts, and lighting poles. Furthermore, the dataset includes sequential frame data obtained from a camera mounted on a vehicle, capturing a total of three hours of driving, encompassing various regions within the city center of Thessaloniki.

In Greece, there are many audiovisual resources available on the Internet that interest scientists and the general public. Although freely available, finding such resources often becomes a challenging task, because they are hosted on scattered websites and in different types/formats. These websites usually offer limited search options; at the same time, there is no aggregation service for audiovisual resources, nor a national registry for such content. To meet this need, the Open AudioVisual Archives project was launched and the first step in its development is to create a dataset with open access audiovisual material. The current research creates such a dataset by applying specific selection criteria in terms of copyright and content, form/use and process/technical characteristics. The results reported in this paper show that libraries, archives, museums, universities, mass media organizations, governmental and non-governmental organizations are the main types of providers, but the vast majority of resources are open courses offered by universities under the “Creative Commons” license. Providers have significant differences in terms of their collection management capabilities. Most of them do not own any kind of publishing infrastructure and use commercial streaming services, such as YouTube. In terms of metadata policy, most of the providers use application profiles instead of international metadata schemas.