Video text tracking for dense and small text based on pp-yoloe-r and sort algorithm
Although end-to-end video text spotting methods based on Transformer can model long-range dependencies and simplify the train process, it will lead to large computation cost with the increase of the frame size in the input video. Therefore, considering the resolution of ICDAR 2023 DSText is 1080 * 1920 and slicing the video frame into several areas will destroy the spatial correlation of text, we divided the small and dense text spotting into two tasks, text detection and tracking. For text detection, we adopt the PP-YOLOE-R which is proven effective in small object detection as our detection model. For text detection, we use the sort algorithm for high inference speed. Experiments on DSText dataset demonstrate that our method is competitive on small and dense text spotting.
Code (0)
등록된 구현이 없습니다.
Tasks
object-detectionObject DetectionSmall Object DetectionText DetectionText SpottingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ICDAR 2023 Video Text Reading Competition for Dense and Small Text
Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., n…
Task 2Text DetectionText SpottingvalidOnline Dense Point Tracking with Streaming Memory
Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video, even in the presence of occlusions. Traditional methods use op…
Optical Flow EstimationPoint TrackingGoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Beyond the text detection and recognition tasks in image text spotting, video text spotting presents an augmented challenge with the inclusion of tracking. While advanced end-to-end trainable methods have shown commendab…
Text DetectionText SpottingDenseTrack: Drone-based Crowd Tracking via Density-aware Motion-appearance Synergy
Drone-based crowd tracking faces difficulties in accurately identifying and monitoring objects from an aerial perspective, largely due to their small size and close proximity to each other, which complicates both localiz…
Crowd CountingLanguage ModelingLanguage ModellingObject LocalizationTowards Universal Modal Tracking with Online Dense Temporal Token Learning
We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+D…