Tingting Li

Dr. Tingting Li

Beijing Forestry University
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 October 2019 in Electronics
Verified
Journal Article
Open access
PDF file
Tingting LiTingting Li
Tingting Li
Enting ZhaoEnting Zhao
Enting Zhao
JZJunguo Zhang
Junguo Zhang
CHChunhe Hu
Chunhe Hu
Recently, many researchers have attempted to use convolutional neural networks (CNNs) for wildfire smoke detection. However, the application of CNNs in wildfire smoke detection still faces several issues, e.g., the high false-alarm rate of detection and the imbalance of training data. To address these issues, we propose a novel framework integrating conventional methods into CNN for wildfire smoke detection, which consisted of a candidate smoke region segmentation strategy and an advanced network architecture, namely wildfire smoke dilated DenseNet (WSDD-Net). Candidate smoke region segmentation removed the complex backgrounds of the wildfire smoke images. The proposed WSDD-Net achieved multi-scale feature extraction by combining dilated convolutions with dense block. In order to solve the problem of the dataset imbalance, an improved cross entropy loss function, namely balanced cross entropy (BCE), was used instead of the original cross entropy loss function in the training process. The proposed WSDD-Net was evaluated according to two smoke datasets, i.e., WS and Yuan, and achieved a high AR (99.20%) and a low FAR (0.24%). The experimental results demonstrated that the proposed framework had better detection capabilities under different negative sample interferences.

9 June 2014 in Textile Research Journal
Verified
Journal Article
Closed access
Tingting LiTingting Li
Tingting Li
RWRui Wang
Rui Wang
CLChing Wen Lou
Ching Wen Lou
JLJan-Yi Lin
Jan-Yi Lin
Jia-Horng LinJia-Horng Lin
Jia-Horng Lin
Through-thickness reinforcement structure of compound fabric was formed through a two-sided needle-punching and thermal-bonding processes. This study presents static and dynamic puncture resistances of compound fabric comprised of Kevlar®/PA6/low-melting PET nonwoven, low-melting PET/PET nonwoven and woven fabric. The effect of the staple fibers fraction on puncture resistance was investigated to assess optimal fiber content in the nonwoven layer. Static and dynamic puncture failure models of non-thermal-bonded and thermal-bonded compound fabrics were constructed using a Weibull probability distribution to predict puncture failure reliability. Result indicates that puncture forces increased and then decreased with low-melting PET fibers, but steadily improved with recycled Kevlar® fibers. Puncture failure probability models show that thermal-bonding largely improved failure reliability of the static puncture property, but slightly decreased dynamic puncture performance. Puncture failure mechanisms were respectively exposed according to SEM observations.

22 February 2022 in Forests
Verified
Journal Article
Open access
PDF file
Tingting LiTingting Li
Tingting Li
CZChangchun Zhang
Changchun Zhang
HZHaowei Zhu
Haowei Zhu
JZJunguo Zhang
Junguo Zhang
Recent advances suggest that deep learning has been widely used to detect smoke for early forest fire warnings. Despite its remarkable success, this approach has a number of problems in real life application. Deep neural networks only learn deep and abstract representations, while ignoring shallow and detailed representations. In addition, previous models have been trained on source domains but have generalized weakly on unseen domains. To cope with these problems, in this paper, we propose an adversarial fusion network (AFN), including a feature fusion network and an adversarial feature-adaptation network for forest fire smoke detection. Specifically, the feature fusion network is able to learn more discriminative representations by fusing abstract and detailed features. Meanwhile, the adversarial feature adaptation network is employed to improve the generalization ability and transfer gains of the AFN. Comprehensive experiments on two self-built forest fire smoke datasets, and three publicly available smoke datasets, validate that our method significantly improves the performance and generalization of smoke detection, particularly the accuracy of the detection of small amounts of smoke.

26 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
YGYingda Guan
Yingda Guan
ZFZhengyang Feng
Zhengyang Feng
HCHuiying Chang
Huiying Chang
KDKuo Du
Kuo Du
Tingting LiTingting Li
Tingting Li
MWMin Wang
Min Wang
We present SDTracker, a method that harnesses the potential of synthetic data for multi-object tracking of real-world scenes in a domain generalization and semi-supervised fashion. First, we use the ImageNet dataset as an auxiliary to randomize the style of synthetic data. With out-of-domain data, we further enforce pyramid consistency loss across different "stylized" images from the same sample to learn domain invariant features. Second, we adopt the pseudo-labeling method to effectively utilize the unlabeled MOT17 training data. To obtain high-quality pseudo-labels, we apply proximal policy optimization (PPO2) algorithm to search confidence thresholds for each sequence. When using the unlabeled MOT17 training set, combined with the pure-motion tracking strategy upgraded via developed post-processing, we finally reach 61.4 HOTA.