| 1. |
- Kristan, Matej, et al.
(author)
-
The Sixth Visual Object Tracking VOT2018 Challenge Results
- 2019
-
In: Computer Vision – ECCV 2018 Workshops. - Cham : Springer Publishing Company. - 9783030110086 - 9783030110093 ; , s. 3-53
-
Conference paper (peer-reviewed)abstract
- The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a “real-time” experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new long-term tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website (http://votchallenge.net).
|
|
| 2. |
- Bhat, Goutam, et al.
(author)
-
NTIRE 2022 Burst Super-Resolution Challenge
- 2022
-
In: 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2022). - : IEEE. - 9781665487399 - 9781665487405 ; , s. 1040-1060
-
Conference paper (peer-reviewed)abstract
- Burst super-resolution has received increased attention in recent years due to its applications in mobile photography. By merging information from multiple shifted images of a scene, burst super-resolution aims to recover details which otherwise cannot be obtained using a simple input image. This paper reviews the NTIRE 2022 challenge on burst super-resolution. In the challenge, the participants were tasked with generating a clean RGB image with 4x higher resolution, given a RAW noisy burst as input. That is, the methods need to perform joint denoising, demosaicking, and super-resolution. The challenge consisted of 2 tracks. Track 1 employed synthetic data, where pixel-accurate high-resolution ground truths are available. Track 2 on the other hand used real-world bursts captured from a handheld camera, along with approximately aligned reference images captured using a DSLR. 14 teams participated in the final testing phase. The top performing methods establish a new state-of-the-art on the burst super-resolution task.
|
|
| 3. |
- Guo, Yangyi, et al.
(author)
-
The use of the general thermal sensation discriminant model based on CNN for room temperature regulation by online brain-computer interface
- 2023
-
In: Building and Environment. - : Elsevier Ltd. - 0360-1323 .- 1873-684X. ; 241
-
Journal article (peer-reviewed)abstract
- Brain-computer interface (BCI) technology can realize dynamic room temperature adjustment based on individual real-time thermal sensation, which can provide the basis for future intelligent buildings. However, the generalization ability of previous thermal sensation discrimination model (TSDM) is limited, which is a serious obstacle to the application. In this paper, a general TSDM was developed by using convolutional neural network (CNN), which can be well applied to new subjects. In the study, the CNN-TSDM was established and evaluated based on the offline experimental data, and then the BCI closed-loop online room temperature control experiment was carried out based on this CNN-TSDM to further verify. The offline analysis results show that the recognition performance of CNN-TSDM in new subjects is significantly higher than that of typical shallow learning algorithms, and its area under the ROC curve (AUC) value reaches 0.789. In the online experiments of the two simulated environments, BCI using the CNN-TSDM dynamically controlled the air conditioning to improve the room temperature to the comfortable level according to the subjects' thermal sensation. The subjective score of subjects decreased from 3.1 to 3.0 for the hot uncomfortable to 1.1 and 1.2 for the cool comfortable (p < 0.001, p < 0.001). Moreover, in a hotter simulated experimental environment, BCI automatically controlled the air conditioner for longer cooling to obtain a same degree of thermal comfort. The total cooling time (p < 0.05) and the single cooling time (p < 0.05) of the air conditioner were significantly increased. This further confirmed the effectiveness and robustness of the general CNN-TSDM.
|
|
| 4. |
- He, Xiaohe, et al.
(author)
-
Real-time regulation of room temperature based on individual thermal sensation using an online brain–computer interface
- 2022
-
In: Indoor Air. - : NLM (Medline). - 0905-6947 .- 1600-0668. ; 32:e13106
-
Journal article (peer-reviewed)abstract
- Regulation of indoor temperature based on neurophysiological and psychological signals is one of the most promising technologies for intelligent buildings. In this study, we developed a system for closed-loop control of indoor temperature based on brain-computer interface (BCI) technology for the first time. Electroencephalogram (EEG) signals were collected from subjects for two room temperature categories (cool comfortable and hot uncomfortable) and used to build a thermal-sensation discrimination model (TSDM) with an ensemble learning method. Then, an online BCI system was developed based on the TSDM. In the online room temperature control experiment, when the TSDM detected that the subjects felt hot and uncomfortable, BCI would automatically turn on the air conditioner, and when the TSDM detected that the subjects felt cool and comfortable, BCI would automatically turn off the air conditioner. The results of online experiments in a hot environment showed that a BCI could significantly improve the thermal comfort of subjects (the subjective thermal comfort score decreased from 2.45 (hot uncomfortable) to 0.55 (cool comfortable), p < 0.001). A parallel experiment further showed that if the subjects wore thicker clothes during the experiment, the BCI would turn on the air conditioner for a longer time to ensure the thermal comfort of the subjects. This has further confirmed the effectiveness of TSDM model in evaluating thermal sensation under the dynamic change of room temperature and showed the model's good robustness. This study proposed a new paradigm of human-building interaction, which is expected to play a promising role in the development of human-centered intelligent buildings.
|
|
| 5. |
- Xie, Xianwei, et al.
(author)
-
Fuel Consumption Prediction Models Based on Machine Learning and Mathematical Methods
- 2023
-
In: Journal of Marine Science and Engineering. - : MDPI. - 2077-1312. ; 11:4
-
Journal article (peer-reviewed)abstract
- An accurate fuel consumption prediction model is the basis for ship navigation status analysis, energy conservation, and emission reduction. In this study, we develop a black-box model based on machine learning and a white-box model based on mathematical methods to predict ship fuel consumption rates. We also apply the Kwon formula as a data preprocessing cleaning method for the black-box model that can eliminate the data generated during the acceleration and deceleration process. The ship model test data and the regression methods are employed to evaluate the accuracy of the models. Furthermore, we use the predicted correlation between fuel consumption rates and speed under simulated conditions for model performance validation. We also discuss applying the data-cleaning method in the preprocessing of the black-box model. The results demonstrate that this method is feasible and can support the performance of the fuel consumption model in a broad and dense distribution of noise data in data collected from real ships. We improved the error to 4% of the white-box model and the R22 to 0.9977 and 0.9922 of the XGBoost and RF models, respectively. After applying the Kwon cleaning method, the value of R22 also can reach 0.9954, which can provide decision support for the operation of shipping companies.
|
|
| 6. |
- Zhang, Qiong, et al.
(author)
-
A series of Zn(II) terpyridine complexes with enhanced two-photon-excited fluorescence for in vitro and in vivo bioimaging
- 2015
-
In: Journal of materials chemistry. B. - : ROYAL SOC CHEMISTRY. - 2050-750X .- 2050-7518. ; 3:36, s. 7213-7221
-
Journal article (peer-reviewed)abstract
- It is still a challenge to obtain two-photon excited fluorescent bioimaging probes with intense emission, high photo-stability and low cytotoxicity. In the present work, four Zn(II)-coordinated complexes (1-4) constructed from two novel D-A and D-p-A ligands (L-1 and L-2) are investigated both experimentally and theoretically, aiming to explore efficient two-photon probes for bioimaging. Molecular geometry optimization used for theoretical calculations is achieved using the crystallographic data. Notably, the results indicate that complexes 1 and 2 display enhanced two-photon absorption (2PA) cross sections compared to their corresponding D-A ligand (L1). Furthermore, it was found that complex 1 has the advantages of moderate 2PA cross section in the near-infrared region, longer fluorescence lifetime, higher quantum yield, good biocompatibility and enhanced two-photon excited fluorescence. Therefore, complex 1 is evaluated as a bioimaging probe for in vitro imaging of HepG2 cells, in which it is observed under a two-photon scanning microscope that complex 1 exhibits effective co-staining with endoplasmic reticulum (ER) and nuclear membrane; as well as for in vivo imaging of zebrafish larva, in which it is observed that complex 1 exhibits specificity in the intestinal system.
|
|
