scholarly journals LSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark

Author(s):  
Qiao Liu ◽  
Xin Li ◽  
Zhenyu He ◽  
Chenglong Li ◽  
Jun Li ◽  
...  
PLoS ONE ◽  
2007 ◽  
Vol 2 (10) ◽  
pp. e1012 ◽  
Author(s):  
Saeid Naderi ◽  
Hamid-Reza Rezaei ◽  
Pierre Taberlet ◽  
Stéphanie Zundel ◽  
Seyed-Abbas Rafat ◽  
...  

Author(s):  
Michael Felsberg ◽  
Matej Kristan ◽  
Jiři Matas ◽  
Aleš Leonardis ◽  
Roman Pflugfelder ◽  
...  

Author(s):  
Matthias Müller ◽  
Adel Bibi ◽  
Silvio Giancola ◽  
Salman Alsubaihi ◽  
Bernard Ghanem

2009 ◽  
Vol 137 (11) ◽  
pp. 4030-4046 ◽  
Author(s):  
Daniel F. Steinhoff ◽  
Saptarshi Chaudhuri ◽  
David H. Bromwich

Abstract A case study illustrating cloud processes and other features associated with the Ross Ice Shelf airstream (RAS), in Antarctica, is presented. The RAS is a semipermanent low-level wind regime primarily over the western Ross Ice Shelf, linked to the midlatitude circulation and formed from terrain-induced and large-scale forcing effects. An integrated approach utilizes Moderate Resolution Imaging Spectroradiometer (MODIS) satellite imagery, automatic weather station (AWS) data, and Antarctic Mesoscale Prediction System (AMPS) forecast output to study the synoptic-scale and mesoscale phenomena involved in cloud formation over the Ross Ice Shelf during a RAS event. A synoptic-scale cyclone offshore of Marie Byrd Land draws moisture across West Antarctica to the southern base of the Ross Ice Shelf. Vertical lifting associated with flow around the Queen Maud Mountains leads to cloud formation that extends across the Ross Ice Shelf to the north. The low-level cloud has a warm signature in thermal infrared imagery, resembling a surface feature of turbulent katabatic flow typically ascribed to the RAS. Strategically placed AWS sites allow assessment of model performance within and outside of the RAS signature. AMPS provides realistic simulation of conditions aloft but experiences problems at low levels due to issues with the model PBL physics. Key meteorological features of this case study, within the context of previous studies on longer time scales, are inferred to be common occurrences. The assumption that warm thermal infrared signatures are surface features is found to be too restrictive.


2020 ◽  
Vol 34 (07) ◽  
pp. 11604-11611 ◽  
Author(s):  
Qiao Liu ◽  
Xin Li ◽  
Zhenyu He ◽  
Nana Fan ◽  
Di Yuan ◽  
...  

Existing deep Thermal InfraRed (TIR) trackers usually use the feature models of RGB trackers for representation. However, these feature models learned on RGB images are neither effective in representing TIR objects nor taking fine-grained TIR information into consideration. To this end, we develop a multi-task framework to learn the TIR-specific discriminative features and fine-grained correlation features for TIR tracking. Specifically, we first use an auxiliary classification network to guide the generation of TIR-specific discriminative features for distinguishing the TIR objects belonging to different classes. Second, we design a fine-grained aware module to capture more subtle information for distinguishing the TIR objects belonging to the same class. These two kinds of features complement each other and recognize TIR objects in the levels of inter-class and intra-class respectively. These two feature models are learned using a multi-task matching framework and are jointly optimized on the TIR tracking task. In addition, we develop a large-scale TIR training dataset to train the network for adapting the model to the TIR domain. Extensive experimental results on three benchmarks show that the proposed algorithm achieves a relative gain of 10% over the baseline and performs favorably against the state-of-the-art methods. Codes and the proposed TIR dataset are available at https://github.com/QiaoLiuHit/MMNet.


2021 ◽  
Vol 41 (6) ◽  
pp. 0615002
Author(s):  
李畅 Li Chang ◽  
杨德东 Yang Dedong ◽  
宋鹏 Song Peng ◽  
郭畅 Guo Chang

2000 ◽  
Vol 6 ◽  
pp. 209-232 ◽  
Author(s):  
Scott L. Wing

Flowering plants are a classic example of a group arising late in Earth history and yet achieving very high diversity, abundance, and ecological and morphological variety in a great array of environments and climatic conditions on all continents. Thus, the success of flowering plants raises basic questions about how new lineages become inserted into existing terrestrial ecosystems. To what degree did flowering plants replace older lineages competitively, and to what extent did their expansion depend on large-scale environmental disruption or extinction of older groups? Is the higher taxonomic diversity of flowering plants a consequence of higher rates of speciation, lower rates of extinction, or both? Have flowering plants expanded the total area and range of habitats occupied by terrestrial vegetation? What were the effects of the diversification and spread of flowering plants on the structure of habitats and the types of resources available to terrestrial heterotrophs?


Sign in / Sign up

Export Citation Format

Share Document