More Like this

1. Improved DeepSORT-Based Object Tracking in Foggy Weather for AVs Using Sematic Labels and Fused Appearance Feature Network

   https://doi.org/10.3390/s24144692  

   Ogunrinde, Isaac; Bernadin, Shonda (July 2024, Sensors)

   The presence of fog in the background can prevent small and distant objects from being detected, let alone tracked. Under safety-critical conditions, multi-object tracking models require faster tracking speed while maintaining high object-tracking accuracy. The original DeepSORT algorithm used YOLOv4 for the detection phase and a simple neural network for the deep appearance descriptor. Consequently, the feature map generated loses relevant details about the track being matched with a given detection in fog. Targets with a high degree of appearance similarity on the detection frame are more likely to be mismatched, resulting in identity switches or track failures in heavy fog. We propose an improved multi-object tracking model based on the DeepSORT algorithm to improve tracking accuracy and speed under foggy weather conditions. First, we employed our camera-radar fusion network (CR-YOLOnet) in the detection phase for faster and more accurate object detection. We proposed an appearance feature network to replace the basic convolutional neural network. We incorporated GhostNet to take the place of the traditional convolutional layers to generate more features and reduce computational complexities and costs. We adopted a segmentation module and fed the semantic labels of the corresponding input frame to add rich semantic information to the low-level appearance feature maps. Our proposed method outperformed YOLOv5 + DeepSORT with a 35.15% increase in multi-object tracking accuracy, a 32.65% increase in multi-object tracking precision, a speed increase by 37.56%, and identity switches decreased by 46.81%. 

   more » « less
2. Attentive Normalization

   https://doi.org/10.1007/978-3-030-58520-4_5  

   Li, X.; Sun, W.; Wu, T. (August 2020, 16th European Conference on Computer Vision (2020))

   Vedaldi, A. (Ed.)

   In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema and present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging channel-wise feature attention. In experiments, we test the proposed AN using four representative neural architectures. In the ImageNet-1000 classification benchmark and the MS-COCO 2017 object detection and instance segmentation benchmark. AN obtains consistent performance improvement for different neural architectures in both benchmarks with absolute increase of top-1 accuracy in ImageNet-1000 between 0.5\% and 2.7\%, and absolute increase up to 1.8\% and 2.2\% for bounding box and mask AP in MS-COCO respectively. We observe that the proposed AN provides a strong alternative to the widely used Squeeze-and-Excitation (SE) module. The source codes are publicly available at \href{https://github.com/iVMCL/AOGNet-v2}{the ImageNet Classification Repo} and \href{https://github.com/iVMCL/AttentiveNorm\_Detection}{the MS-COCO Detection and Segmentation Repo}. 

   more » « less
3. PIXEL-WISE NEURAL CELL INSTANCE SEGMENTATION

   Yi, J.; Wu, P.; Hoeppner, D. J.; Metaxas, D. (April 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018))

   Accurate cell instance segmentation plays an important role in the study of neural cell interactions, which are critical for understanding the development of brain. These interactions are performed through the filopodia and lamellipodia of neural cells, which are extremely tiny structures and as a result render most existing instance segmentation methods powerless to precisely capture them. To solve this issue, in this paper we present a novel hierarchical neural network comprising object detection and segmentation modules. Compared to previous work, our model is able to efficiently share and make full use of the information at different levels between the two modules. Our method is simple yet powerful, and experimental results show that it captures the contours of neural cells, especially the filopodia and lamellipodia, with high accuracy, and outperforms recent state of the art by a large margin. 

   more » « less
4. DropConnect is effective in modeling uncertainty of Bayesian deep networks

   https://doi.org/10.1038/s41598-021-84854-x  

   Mobiny, Aryan; Yuan, Pengyu; Moulik, Supratik K.; Garg, Naveen; Wu, Carol C.; Van Nguyen, Hien (December 2021, Scientific Reports)

   null (Ed.)

   Abstract Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art. 

   more » « less
5. Monocularly Generated 3D High Level Semantic Model by Integrating Deep Learning Models and Traditional Vision Techniques

   https://doi.org/10.1109/IST50367.2021.9651471  

   Alsheimer, Steven; Zhu, Zhigang (August 2021, 2021 IEEE International Conference on Imaging Systems and Techniques (IST))

   Scene reconstruction using Monodepth2 (Monocular Depth Inference) which provides depth maps from a single RGB camera, the outputs are filled with noise and inconsistencies. Instance segmentation using a Mask R-CNN (Region Based Convolution Neural Networks) deep model can provide object segmentation results in 2D but lacks 3D information. In this paper we propose to integrate the results of Instance segmentation via Mask R-CNN’s, CAD model Car Shape Alignment, and depth from Monodepth2 together with classical dynamic vision techniques to create a High-level Semantic Model with separability, robustness, consistency and saliency. The model is useful for both virtualized rendering, semantic augmented reality and automatic driving. Experimental results are provided to validate the approach. 

   more » « less