method: h&h_VideoText_test2019-12-21

Authors: DianJin,...

Affiliation: h&h

Description: A primary test

method: SRC-B-TextProcessingLab2016-04-14

Authors: SRC-B-TextProcessingLab

Description:

method: AJOU2015-04-01

Authors: Hyung Il Koo and Yong Gyun Kim

Description: This text detection and tracking system was submitted by Hyung Il Koo and Yong Gyun Kim from Ajou University, Suwon, Korea. The system first extracts connected components (CCs) with the maximally stable extremal region (MSER) algorithm and finds word candidates by using the bottom-up grouping clustering method [1]. For each candidate region, we find corresponding regions in the other frames with the CSK trackers [2] and build chains. We also detect collisions between the chains and filter out non-promising ones.
[1] Hyung Il Koo and Duck Hoon Kim, "Scene Text Detection via Connected Component Clustering and Nontext Filtering," IEEE Transactions on Image Processing, vol.22, no.6, pp.2296,2305, June 2013
[2] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, “Exploiting the Circulant Structure of Tracking-by-detection with Kernels,”, ECCV 2012

Ranking Table

Description Paper Source Code
DateMethodMOTAMOTPIDF1Mostly MatchedPartially MatchedMostly Lost
2019-12-21h&h_VideoText_test38.67%73.65%57.24%753605558
2016-04-14SRC-B-TextProcessingLab23.09%68.51%39.40%2744811161
2015-04-01AJOU16.44%72.71%36.07%2714581187
2015-04-02USTB_TexVideo II-212.29%71.78%21.93%924391385
2016-04-13Megvii-Image++11.02%66.75%37.30%1856121119
2015-04-17StradVision-17.92%70.17%25.87%1244361356
2015-04-02USTB_TexVideo7.42%70.75%25.92%1425071267
2015-04-02USTB_TexVideo II-1-59.62%69.06%17.59%1293681419
2015-03-28RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2)-106.48%64.64%3.45%473081561

Ranking Graphic