Hae Young Noh

Jingxiao Liu, Yujie Wei, Bingqing Chen et al.

Computer vision-based damage detection using remote cameras and unmanned aerial vehicles (UAVs) enables efficient and low-cost bridge health monitoring that reduces labor costs and the needs for sensor installation and maintenance. By leveraging recent semantic image segmentation approaches, we are able to find regions of critical structural components and recognize damage at the pixel level using images as the only input. However, existing methods perform poorly when detecting small damages (e.g., cracks and exposed rebars) and thin objects with limited image samples, especially when the components of interest are highly imbalanced. To this end, this paper introduces a semantic segmentation framework that imposes the hierarchical semantic relationship between component category and damage types. For example, certain concrete cracks only present on bridge columns and therefore the non-column region will be masked out when detecting such damages. In this way, the damage detection model could focus on learning features from possible damaged regions only and avoid the effects of other irrelevant regions. We also utilize multi-scale augmentation that provides views with different scales that preserves contextual information of each image without losing the ability of handling small and thin objects. Furthermore, the proposed framework employs important sampling that repeatedly samples images containing rare components (e.g., railway sleeper and exposed rebars) to provide more data samples, which addresses the imbalanced data challenge.

Xuechun Li, Paula M. Burgi, Wei Ma et al.

Onsite disasters like earthquakes can trigger cascading hazards and impacts, such as landslides and infrastructure damage, leading to catastrophic losses; thus, rapid and accurate estimates are crucial for timely and effective post-disaster responses. Interferometric Synthetic aperture radar (InSAR) data is important in providing high-resolution onsite information for rapid hazard estimation. Most recent methods using InSAR imagery signals predict a single type of hazard and thus often suffer low accuracy due to noisy and complex signals induced by co-located hazards, impacts, and irrelevant environmental changes (e.g., vegetation changes, human activities). We introduce a novel stochastic variational inference with normalizing flows derived to jointly approximate posteriors of multiple unobserved hazards and impacts from noisy InSAR imagery.

Yiwen Dong, Hae Young Noh

Person identification is important for smart buildings to provide personalized services such as health monitoring, activity tracking, and personnel management. However, previous person identification relies on pre-collected data from everyone, which is impractical in many buildings and public facilities in which visitors are typically expected. This calls for a continual person identification system that gradually learns people's identities on the fly. Existing studies use cameras to achieve this goal, but they require direct line-of-sight and also have raised privacy concerns in public. Other modalities such as wearables and pressure mats are limited by the requirement of device-carrying or dense deployment. Thus, prior studies introduced footstep-induced structural vibration sensing, which is non-intrusive and perceived as more privacy-friendly. However, this approach has a significant challenge: the high variability of vibration data due to structural heterogeneity and human gait variations, which makes online person identification algorithms perform poorly. In this paper, we characterize the variability in footstep-induced structural vibration data for accurate online person identification. To achieve this, we quantify and decompose different sources of variability and then design a feature transformation function to reduce the variability within each person's data to make different people's data more separable. We evaluate our approach through field experiments with 20 people. The results show a 70% variability reduction and a 90% accuracy for online person identification.

Yuyan Wu, Hae Young Noh

Detecting road boundaries, the static physical edges of the available driving area, is important for safe navigation and effective path planning in autonomous driving and advanced driver-assistance systems (ADAS). Traditionally, road boundary detection in autonomous driving relies on cameras and LiDAR. However, they are vulnerable to poor lighting conditions, such as nighttime and direct sunlight glare, or prohibitively expensive for low-end vehicles. To this end, this paper introduces 4DRadarRBD, the first road boundary detection method based on 4D mmWave radar which is cost-effective and robust in complex driving scenarios. The main idea is that road boundaries (e.g., fences, bushes, roadblocks), reflect millimeter waves, thus generating point cloud data for the radar. To overcome the challenge that the 4D mmWave radar point clouds contain many noisy points, we initially reduce noisy points via physical constraints for road boundaries and then segment the road boundary points from the noisy points by incorporating a distance-based loss which penalizes for falsely detecting the points far away from the actual road boundaries. In addition, we capture the temporal dynamics of point cloud sequences by utilizing each point's deviation from the vehicle motion-compensated road boundary detection result obtained from the previous frame, along with the spatial distribution of the point cloud for point-wise road boundary segmentation. We evaluated 4DRadarRBD through real-world driving tests and achieved a road boundary point segmentation accuracy of 93$\%$, with a median distance error of up to 0.023 m and an error reduction of 92.6$\%$ compared to the baseline model.

Yen Cheng Chang, Jesse Codling, Yiwen Dong et al.

Crowd monitoring in sports stadiums is important to enhance public safety and improve the audience experience. Existing approaches mainly rely on cameras and microphones, which can cause significant disturbances and often raise privacy concerns. In this paper, we sense floor vibration, which provides a less disruptive and more non-intrusive way of crowd sensing, to predict crowd behavior. However, since the vibration-based crowd monitoring approach is newly developed, one main challenge is the lack of training data due to sports stadiums being large public spaces with complex physical activities. In this paper, we present ViLA (Vibration Leverage Audio), a vibration-based method that reduces the dependency on labeled data by pre-training with unlabeled cross-modality data. ViLA is first pre-trained on audio data in an unsupervised manner and then fine-tuned with a minimal amount of in-domain vibration data. By leveraging publicly available audio datasets, ViLA learns the wave behaviors from audio and then adapts the representation to vibration, reducing the reliance on domain-specific vibration data. Our real-world experiments demonstrate that pre-training the vibration model using publicly available audio data (YouTube8M) achieved up to a 5.8x error reduction compared to the model without audio pre-training.

Yiwen Dong, Jessica Rose, Hae Young Noh

Quantitative estimation of human joint motion in daily living spaces is essential for early detection and rehabilitation tracking of neuromusculoskeletal disorders (e.g., Parkinson's) and mitigating trip and fall risks for older adults. Existing approaches involve monitoring devices such as cameras, wearables, and pressure mats, but have operational constraints such as direct line-of-sight, carrying devices, and dense deployment. To overcome these limitations, we leverage gait-induced floor vibration to estimate lower-limb joint motion (e.g., ankle, knee, and hip flexion angles), allowing non-intrusive and contactless gait health monitoring in people's living spaces. To overcome the high uncertainty in lower-limb movement given the limited information provided by the gait-induced floor vibrations, we formulate a physics-informed graph to integrate domain knowledge of gait biomechanics and structural dynamics into the model. Specifically, different types of nodes represent heterogeneous information from joint motions and floor vibrations; Their connecting edges represent the physiological relationships between joints and forces governed by gait biomechanics, as well as the relationships between forces and floor responses governed by the structural dynamics. As a result, our model poses physical constraints to reduce uncertainty while allowing information sharing between the body and the floor to make more accurate predictions. We evaluate our approach with 20 participants through a real-world walking experiment. We achieved an average of 3.7 degrees of mean absolute error in estimating 12 joint flexion angles (38% error reduction from baseline), which is comparable to the performance of cameras and wearables in current medical practices.

Ankit Shrivastava, Jingxiao Liu, Kaushik Dayal et al.

This work presents a machine learning approach to predict peak-stress clusters in heterogeneous polycrystalline materials. Prior work on using machine learning in the context of mechanics has largely focused on predicting the effective response and overall structure of stress fields. However, their ability to predict peak stresses -- which are of critical importance to failure -- is unexplored, because the peak-stress clusters occupy a small spatial volume relative to the entire domain, and hence requires computationally expensive training. This work develops a deep-learning based Convolutional Encoder-Decoder method that focuses on predicting peak-stress clusters, specifically on the size and other characteristics of the clusters in the framework of heterogeneous linear elasticity. This method is based on convolutional filters that model local spatial relations between microstructures and stress fields using spatially weighted averaging operations. The model is first trained against linear elastic calculations of stress under applied macroscopic strain in synthetically-generated microstructures, which serves as the ground truth. The trained model is then applied to predict the stress field given a (synthetically-generated) microstructure and then to detect peak-stress clusters within the predicted stress field. The accuracy of the peak-stress predictions is analyzed using the cosine similarity metric and by comparing the geometric characteristics of the peak-stress clusters against the ground-truth calculations. It is observed that the model is able to learn and predict the geometric details of the peak-stress clusters and, in particular, performed better for higher (normalized) values of the peak stress as compared to lower values of the peak stress. These comparisons showed that the proposed method is well-suited to predict the characteristics of peak-stress clusters.

Jingxiao Liu, Susu Xu, Mario Bergés et al.

Monitoring bridge health using vibrations of drive-by vehicles has various benefits, such as no need for directly installing and maintaining sensors on the bridge. However, many of the existing drive-by monitoring approaches are based on supervised learning models that require labeled data from every bridge of interest, which is expensive and time-consuming, if not impossible, to obtain. To this end, we introduce a new framework that transfers the model learned from one bridge to diagnose damage in another bridge without any labels from the target bridge. Our framework trains a hierarchical neural network model in an adversarial way to extract task-shared and task-specific features that are informative to multiple diagnostic tasks and invariant across multiple bridges. We evaluate our framework on experimental data collected from 2 bridges and 3 vehicles. We achieve accuracies of 95% for damage detection, 93% for localization, and up to 72% for quantification, which are ~2 times improvements from baseline methods.

Jingxiao Liu, Mario Bergés, Jacobo Bielak et al.

Monitoring bridge health using the vibrations of drive-by vehicles has various benefits, such as low cost and no need for direct installation or on-site maintenance of equipment on the bridge. However, many such approaches require labeled data from every bridge, which is expensive and time-consuming, if not impossible, to obtain. This is further exacerbated by having multiple diagnostic tasks, such as damage quantification and localization. One way to address this issue is to directly apply the supervised model trained for one bridge to other bridges, although this may significantly reduce the accuracy because of distribution mismatch between different bridges'data. To alleviate these problems, we introduce a transfer learning framework using domain-adversarial training and multi-task learning to detect, localize and quantify damage. Specifically, we train a deep network in an adversarial way to learn features that are 1) sensitive to damage and 2) invariant to different bridges. In addition, to improve the error propagation from one task to the next, our framework learns shared features for all the tasks using multi-task learning. We evaluate our framework using lab-scale experiments with two different bridges. On average, our framework achieves 94%, 97% and 84% accuracy for damage detection, localization and quantification, respectively. within one damage severity level.

Madhumitha Harishankar, Jun Han, Sai Vineeth Kalluru Srinivas et al.

The resolution of GPS measurements, especially in urban areas, is insufficient for identifying a vehicle's lane. In this work, we develop a deep LSTM neural network model LaNet that determines the lane vehicles are on by periodically classifying accelerometer samples collected by vehicles as they drive in real time. Our key finding is that even adjacent patches of road surfaces contain characteristics that are sufficiently unique to differentiate between lanes, i.e., roads inherently exhibit differing bumps, cracks, potholes, and surface unevenness. Cars can capture this road surface information as they drive using inexpensive, easy-to-install accelerometers that increasingly come fitted in cars and can be accessed via the CAN-bus. We collect an aggregate of 60 km driving data and synthesize more based on this that capture factors such as variable driving speed, vehicle suspensions, and accelerometer noise. Our formulated LSTM-based deep learning model, LaNet, learns lane-specific sequences of road surface events (bumps, cracks etc.) and yields 100% lane classification accuracy with 200 meters of driving data, achieving over 90% with just 100 m (correspondingly to roughly one minute of driving). We design the LaNet model to be practical for use in real-time lane classification and show with extensive experiments that LaNet yields high classification accuracy even on smooth roads, on large multi-lane roads, and on drives with frequent lane changes. Since different road surfaces have different inherent characteristics or entropy, we excavate our neural network model and discover a mechanism to easily characterize the achievable classification accuracies in a road over various driving distances by training the model just once. We present LaNet as a low-cost, easily deployable and highly accurate way to achieve fine-grained lane identification.

Asim Smailagic, Pedro Costa, Alex Gaudio et al.

Active Learning methods create an optimized labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results in this paper. Our novel sampling method queries the unlabeled examples that maximize the average distance to all training set examples. Our online method enhances performance of its underlying baseline deep network. These novelties contribute significant performance improvements, including improving the model's underlying deep network accuracy by 6.30%, using only 25% of the labeled dataset to achieve baseline accuracy, reducing backpropagated images during training by as much as 67%, and demonstrating robustness to class imbalance in binary and multi-class tasks.

Asim Smailagic, Hae Young Noh, Pedro Costa et al.

Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance.Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance. However, such large labeled datasets are costly to acquire. Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance.In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space. We then extend our sampling method to define a better initial training set, without the need for a trained model, by using ORB feature descriptors. We validate MedAL on 3 medical image datasets and show that our method is robust to different dataset properties. MedAL is also efficient, achieving 80% accuracy on the task of Diabetic Retinopathy detection using only 425 labeled images, corresponding to a 32% reduction in the number of required labeled examples compared to the standard uncertainty sampling technique, and a 40% reduction compared to random sampling.

Lex Fridman, Daniel E Brown, William Angell et al.

We propose a method for automated synchronization of vehicle sensors useful for the study of multi-modal driver behavior and for the design of advanced driver assistance systems. Multi-sensor decision fusion relies on synchronized data streams in (1) the offline supervised learning context and (2) the online prediction context. In practice, such data streams are often out of sync due to the absence of a real-time clock, use of multiple recording devices, or improper thread scheduling and data buffer management. Cross-correlation of accelerometer, telemetry, audio, and dense optical flow from three video sensors is used to achieve an average synchronization error of 13 milliseconds. The insight underlying the effectiveness of the proposed approach is that the described sensors capture overlapping aspects of vehicle vibrations and vehicle steering allowing the cross-correlation function to serve as a way to compute the delay shift in each sensor. Furthermore, we show the decrease in synchronization error as a function of the duration of the data stream.