Pedestrian tracking is a challenging task in the area of visual object tracking research and it is a vital component of various vision-based applications such as surveillance systems, human-following robots, and autonomous vehicles. In this paper, we proposed a single pedestrian tracking (SPT) framework for identifying each instance of a person across all video frames through a tracking-by-detection paradigm that combines deep learning and metric learning-based approaches. The SPT framework comprises three main modules: detection, re-identification, and tracking. Our contribution is a significant improvement in the results by designing two compact metric learning-based models using Siamese architecture in the pedestrian re-identification module and combining one of the most robust re-identification models for data associated with the pedestrian detector in the tracking module. We carried out several analyses to evaluate the performance of our SPT framework for single pedestrian tracking in the videos. The results of the re-identification module validate that our two proposed re-identification models surpass existing state-of-the-art models with increased accuracies of 79.2% and 83.9% on the large dataset and 92% and 96% on the small dataset. Moreover, the proposed SPT tracker, along with six state-of-the-art (SOTA) tracking models, has been tested on various indoor and outdoor video sequences. A qualitative analysis considering six major environmental factors verifies the effectiveness of our SPT tracker under illumination changes, appearance variations due to pose changes, changes in target position, and partial occlusions. In addition, quantitative analysis based on experimental results also demonstrates that our proposed SPT tracker outperforms the GOTURN, CSRT, KCF, and SiamFC trackers with a success rate of 79.7% while beating the DiamSiamRPN, SiamFC, CSRT, GOTURN, and SiamMask trackers with an average of 18 tracking frames per second.

본 논문에서는 객체 탐지와 광학 문자 인식(이하 OCR)을 복합적으로 사용하여 책장 내의 다수의 책이 꽂혀 있을 때 책등을 탐지하여 책 제목을 추출하고 이를 통해 책에 대한 추가적인 정보를 확인할 수 있는 모델을 구현한 결과에 대해 다루고 있다. 객체 탐지 과정은 책등과 책 제목 영역 탐지로 단계를 분리하였고 2개의 Yolov5 모델을 사용하여 객체 탐지에 대한 성능을 높였다. OCR 단계에서는 출력되는 텍스트의 정확도를 높이기 위하여 이미지가 OCR 모델에 입력되기 전 단계에서 흑백 변환, 크기 변환, 밝기 조절과 같은 전처리를 수행하였다. 느린 OCR 처리 시간에 대한 문제를 보완하기 위해 설계한 모델을 웹 애플리케이션에 적용하는 과정에서 사용자가 원하는 책을 선택하는 기능을 추가하였다. 추가적으로 객체 탐지와 광학 문자 인식을 통해 추출된 제목을 이용해 저자, 출판사, 가격, 후기와 같은 정보를 확인할 수 있도록 하였다.

We propose a novel geometry-constrained learning-based method for camera-in-hand visual servoing systems that eliminates the need for camera intrinsic parameters, depth information, and the robot’s kinematic model. Our method uses a cerebellar model articulation controller (CMAC) to execute online Jacobian estimation within the control framework. Specifically, we introduce a fixed-dimension, uniform-magnitude error function based on the projective homography matrix. The fixed-dimension error function ensures a constant Jacobian size regardless of the number of feature points, thereby reducing computational complexity. By not relying on individual feature points, the approach maintains robustness even when some features are occluded. The uniform magnitude of the error vector elements simplifies neural network input normalization, thereby enhancing online training efficiency. Furthermore, we incorporate geometric constraints between feature points (such as collinearity preservation) into the network update process, ensuring that model predictions conform to the fundamental principles of projective geometry and eliminating physically impossible control outputs. Experimental and simulation results demonstrate that our approach achieves superior robustness and faster learning rates compared to other model-free image-based visual servoing methods.

Indoor service and inspection robots need environment knowledge that is queryable, reliable, and maintainable as the site changes, yet open-vocabulary 3D pipelines propagate unverified labels downstream and build-once scene models offer no maintenance path. We present TLS-SMF, a semantic modeling framework that converts registered terrestrial laser scans into a confidence-aware semantic knowledge graph and keeps it current across repeated scans. TLS-SMF combines (i) a deterministic geometric backbone whose re-runs are byte-identical on the same host, (ii) multi-view vision–language-model verification with automatic escalation that retains unresolved objects as explicitly unverified, and (iii) identity-preserving incremental updates that apply confidence-gated node-level upserts to mint-once node identities. Across two operational configurations of one industrial room, escalation lifts verification accuracy from 77.8% to 88.9% and from 78.1% to 84.4%, with 94.4–100% unanimous-vote precision against confirmed owner ground truth; on the showroom benchmark, structurally gated querying answers 83.3% of questions versus 52.1% for an unverified Stage-A LLM baseline while blocking hallucination traps; in a controlled same-quality combined-edit re-scan, selective re-verification reduces VLM cost to 3.1% of a full rebuild; and a real three-epoch study detects 2/2 controlled physical changes with zero observed identity switches on strong reference correspondences, while re-segmentation still produces false-new/false-absent cases. A cross-floor cafeteria stress scene bounds domain transfer, and an owner-in-the-loop revision path keeps the single semantic store corrigible for robot-facing use; the same store drives a physical mobile manipulator, which completes three console-issued semantic missions with a mean arrival error of 0.30 m while phantom goals are refused with zero motion.

Automated three-dimensional (3D) mapping with a survey-grade terrestrial laser scanner (TLS) is the canonical instance of robotic stop-and-scan light detection and ranging (LiDAR) mapping: the mobile platform must remain stationary for minutes per scan, so the environment must be covered with as few scans as possible. Where to stop hinges on a coverage model predicting what a scan pose will observe. The conventional isotropic-disk model counts every free cell within sensing range as covered—including cells behind walls—and, therefore, skips scans that genuine observation requires. We replace the disk with a ray-cast visibility region computed on the robot’s live two-dimensional (2D) occupancy map, admitting only cells in direct line of sight; define a line-of-sight (LOS) coverage metric over mapped free space and drive a marginal-gain scan/skip rule embedded in frontier exploration. The planner thus performs 2D scan-station placement for subsequent 3D mapping. In a controlled paired ablation in simulation, the visibility rule raises LOS coverage from about 77% to 84–85% for one to two additional scans, and it also outperforms a disk baseline governed by the identical marginal-gain rule, isolating the coverage model itself as the decisive factor. In a fully autonomous on-hardware comparison in an industrial test room, with each rule driving a mobile platform carrying a Leica BLK360 G1, the visibility rule raised LOS coverage from 77.6% to 92.1%; every visibility run’s scans registered offline at survey grade (4–5 mm bundle error, 84–88% overlap), whereas disk runs yielded at best a single-link network and once a single unregistrable scan. The results indicate that, for the room-scale indoor environments studied, occlusion-aware visibility is a sounder basis than Euclidean proximity for stop-and-scan placement.