arXiv subjects

Siyang Cao

Publications and source records attributed to Siyang Cao.

17 recordsLinked to original sources

arXiv2026

CLIFE: Camera-LiDAR Fusion Framework for Edge-Deployable Roadside VRU Perception

Reliable roadside perception of vulnerable road users (VRUs) remains challenging under occlusions, variable lighting, and diverse weather conditions, particularly under strict edge-computing and latency constraints. Existing multi-sensor fusion systems rely on cloud or server-grade infrastructure, creating a deployment gap at real-world intersections. We present CLIFE, an edge-native camera-LiDAR fusion framework that integrates targetless online calibration and lightweight late-fusion tracking entirely on a single embedded device, without cloud offloading. CLIFE adaptively refines camera-LiDAR alignment on demand and performs multi-sensor fusion and track association with O(N log N) per-frame cost. We deploy CLIFE across 12 signalized intersections in Chattanooga and conduct an in-depth evaluation at a representative intersection using synchronized camera-LiDAR data that spans diverse daytime, nighttime, and weather conditions. Our experiments demonstrate that the fusion architecture substantially enhances the perceptual range and robustness of the individual sensors under varied environmental and traffic conditions. The late-fusion core operates at 53.2 FPS on the Jetson AGX Thor, ensuring high throughput for real-time intersection-scale applications. By centering perception at the edge, CLIFE provides a deployable foundation for downstream safety applications, while reducing bandwidth and calibration overhead for agencies operating multi-intersection corridors.

cs.CV↗

arXiv2026

Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors

Large language models often produce hallucinated answers that violate prompt-level constraints. A key diagnostic question is whether these failures reflect missing knowledge, or whether the model has the relevant information but follows the wrong inference path. We study this phenomenon as inference misalignment: a mismatch between the answer supported by the prompt and the answer favored by statistically salient latent associations. We formalize this view with a latent key-task model, in which pretraining-frequency imbalance can cause a shortcut path to dominate the constraint-sensitive path and induce positive inference loss. The framework predicts two failure modes: task-retrieval bias in entity disambiguation and key-selection bias in action choice. We introduce TrapQA, a controlled diagnostic testbed with two components. ScientistQA tests disambiguation among similar scientists with supplementary factual probes, while Real-Life Constrained QA tests everyday constraint following under salient shortcuts. Our results show that hallucination can arise from biased latent inference rather than absent knowledge alone.

cs.CL↗

arXiv2026

Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning

Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contributions. We propose Preference Coordinated Multi-agent Policy Optimization (PCMA), which learns coordinated agent-specific preferences to enable complementary trade-offs among agents. Theoretically, we formulate cooperative MOMARL as a team-optimal game and show that, under suitable conditions, preference diversity can induce team improvement through a first-order improvement decomposition. Experiments on multiple cooperative MOMA environments and a practical traffic-control scenario show that PCMA improves both performance and trade-off coordination.

cs.MA↗

arXiv2025

Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature

This paper presents a Multi-Object Tracking (MOT) framework that fuses radar and camera data to enhance tracking efficiency while minimizing manual interventions. Contrary to many studies that underutilize radar and assign it a supplementary role--despite its capability to provide accurate range/depth information of targets in a world 3D coordinate system--our approach positions radar in a crucial role. Meanwhile, this paper utilizes common features to enable online calibration to autonomously associate detections from radar and camera. The main contributions of this work include: (1) the development of a radar-camera fusion MOT framework that exploits online radar-camera calibration to simplify the integration of detection results from these two sensors, (2) the utilization of common features between radar and camera data to accurately derive real-world positions of detected objects, and (3) the adoption of feature matching and category-consistency checking to surpass the limitations of mere position matching in enhancing sensor association accuracy. To the best of our knowledge, we are the first to investigate the integration of radar-camera common features and their use in online calibration for achieving MOT. The efficacy of our framework is demonstrated by its ability to streamline the radar-camera mapping process and improve tracking precision, as evidenced by real-world experiments conducted in both controlled environments and actual traffic scenarios. Code is available at https://github.com/radar-lab/Radar_Camera_MOT

cs.CV↗

arXiv2025

CalibRefine: Deep Learning-Based Online Automatic Targetless LiDAR-Camera Calibration with Iterative and Attention-Driven Post-Refinement

Accurate multi-sensor calibration is essential for deploying robust perception systems in applications such as autonomous driving and intelligent transportation. Existing LiDAR-camera calibration methods often rely on manually placed targets, preliminary parameter estimates, or intensive data preprocessing, limiting their scalability and adaptability in real-world settings. In this work, we propose a fully automatic, targetless, and online calibration framework, CalibRefine, which directly processes raw LiDAR point clouds and camera images. Our approach is divided into four stages: (1) a Common Feature Discriminator that leverages relative spatial positions, visual appearance embeddings, and semantic class cues to identify and generate reliable LiDAR-camera correspondences, (2) a coarse homography-based calibration that uses the matched feature correspondences to estimate an initial transformation between the LiDAR and camera frames, serving as the foundation for further refinement, (3) an iterative refinement to incrementally improve alignment as additional data frames become available, and (4) an attention-based refinement that addresses non-planar distortions by leveraging a Vision Transformer and cross-attention mechanisms. Extensive experiments on two urban traffic datasets demonstrate that CalibRefine achieves high-precision calibration with minimal human input, outperforming state-of-the-art targetless methods and matching or surpassing manually tuned baselines. Our results show that robust object-level feature matching, combined with iterative refinement and self-supervised attention-based refinement, enables reliable sensor alignment in complex real-world conditions without ground-truth matrices or elaborate preprocessing. Code is available at https://github.com/radar-lab/Lidar_Camera_Automatic_Calibration

cs.CV↗

arXiv2025

TransRAD: Retentive Vision Transformer for Enhanced Radar Object Detection

Despite significant advancements in environment perception capabilities for autonomous driving and intelligent robotics, cameras and LiDARs remain notoriously unreliable in low-light conditions and adverse weather, which limits their effectiveness. Radar serves as a reliable and low-cost sensor that can effectively complement these limitations. However, radar-based object detection has been underexplored due to the inherent weaknesses of radar data, such as low resolution, high noise, and lack of visual information. In this paper, we present TransRAD, a novel 3D radar object detection model designed to address these challenges by leveraging the Retentive Vision Transformer (RMT) to more effectively learn features from information-dense radar Range-Azimuth-Doppler (RAD) data. Our approach leverages the Retentive Manhattan Self-Attention (MaSA) mechanism provided by RMT to incorporate explicit spatial priors, thereby enabling more accurate alignment with the spatial saliency characteristics of radar targets in RAD data and achieving precise 3D radar detection across Range-Azimuth-Doppler dimensions. Furthermore, we propose Location-Aware NMS to effectively mitigate the common issue of duplicate bounding boxes in deep radar object detection. The experimental results demonstrate that TransRAD outperforms state-of-the-art methods in both 2D and 3D radar detection tasks, achieving higher accuracy, faster inference speed, and reduced computational complexity. Code is available at https://github.com/radar-lab/TransRAD

cs.CV↗

arXiv2024

mmWave Radar for Sit-to-Stand Analysis: A Comparative Study with Wearables and Kinect

This study explores a novel approach for analyzing Sit-to-Stand (STS) movements using millimeter-wave (mmWave) radar technology. The goal is to develop a non-contact sensing, privacy-preserving, and all-day operational method for healthcare applications, including fall risk assessment. We used a 60GHz mmWave radar system to collect radar point cloud data, capturing STS motions from 45 participants. By employing a deep learning pose estimation model, we learned the human skeleton from Kinect built-in body tracking and applied Inverse Kinematics (IK) to calculate joint angles, segment STS motions, and extract commonly used features in fall risk assessment. Radar extracted features were then compared with those obtained from Kinect and wearable sensors. The results demonstrated the effectiveness of mmWave radar in capturing general motion patterns and large joint movements (e.g., trunk). Additionally, the study highlights the advantages and disadvantages of individual sensors and suggests the potential of integrated sensor technologies to improve the accuracy and reliability of motion analysis in clinical and biomedical research settings.

eess.SP↗

arXiv2024

Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensors

Autonomous driving holds great promise in addressing traffic safety concerns by leveraging artificial intelligence and sensor technology. Multi-Object Tracking plays a critical role in ensuring safer and more efficient navigation through complex traffic scenarios. This paper presents a novel deep learning-based method that integrates radar and camera data to enhance the accuracy and robustness of Multi-Object Tracking in autonomous driving systems. The proposed method leverages a Bi-directional Long Short-Term Memory network to incorporate long-term temporal information and improve motion prediction. An appearance feature model inspired by FaceNet is used to establish associations between objects across different frames, ensuring consistent tracking. A tri-output mechanism is employed, consisting of individual outputs for radar and camera sensors and a fusion output, to provide robustness against sensor failures and produce accurate tracking results. Through extensive evaluations of real-world datasets, our approach demonstrates remarkable improvements in tracking accuracy, ensuring reliable performance even in low-visibility scenarios.

cs.CV↗

arXiv2024

Online Targetless Radar-Camera Extrinsic Calibration Based on the Common Features of Radar and Camera

Sensor fusion is essential for autonomous driving and autonomous robots, and radar-camera fusion systems have gained popularity due to their complementary sensing capabilities. However, accurate calibration between these two sensors is crucial to ensure effective fusion and improve overall system performance. Calibration involves intrinsic and extrinsic calibration, with the latter being particularly important for achieving accurate sensor fusion. Unfortunately, many target-based calibration methods require complex operating procedures and well-designed experimental conditions, posing challenges for researchers attempting to reproduce the results. To address this issue, we introduce a novel approach that leverages deep learning to extract a common feature from raw radar data (i.e., Range-Doppler-Angle data) and camera images. Instead of explicitly representing these common features, our method implicitly utilizes these common features to match identical objects from both data sources. Specifically, the extracted common feature serves as an example to demonstrate an online targetless calibration method between the radar and camera systems. The estimation of the extrinsic transformation matrix is achieved through this feature-based approach. To enhance the accuracy and robustness of the calibration, we apply the RANSAC and Levenberg-Marquardt (LM) nonlinear optimization algorithm for deriving the matrix. Our experiments in the real world demonstrate the effectiveness and accuracy of our proposed method.

cs.RO↗

arXiv2023

A Survey on Radar-Based Fall Detection

Fall detection, particularly critical for high-risk demographics like the elderly, is a key public health concern where timely detection can greatly minimize harm. With the advancements in radio frequency technology, radar has emerged as a powerful tool for human detection and tracking. Traditional machine learning algorithms, such as Support Vector Machines (SVM) and k-Nearest Neighbors (kNN), have shown promising outcomes. However, deep learning approaches, notably Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), have outperformed in learning intricate features and managing large, unstructured datasets. This survey offers an in-depth analysis of radar-based fall detection, with emphasis on Micro-Doppler, Range-Doppler, and Range-Doppler-Angles techniques. We discuss the intricacies and challenges in fall detection and emphasize the necessity for a clear definition of falls and appropriate detection criteria, informed by diverse influencing factors. We present an overview of radar signal processing principles and the underlying technology of radar-based fall detection, providing an accessible insight into machine learning and deep learning algorithms. After examining 74 research articles on radar-based fall detection published since 2000, we aim to bridge current research gaps and underscore the potential future research strategies, emphasizing the real-world applications possibility and the unexplored potential of deep learning in improving radar-based fall detection.

cs.RO↗

arXiv2023

3D Radar and Camera Co-Calibration: A Flexible and Accurate Method for Target-based Extrinsic Calibration

Advances in autonomous driving are inseparable from sensor fusion. Heterogeneous sensors are widely used for sensor fusion due to their complementary properties, with radar and camera being the most equipped sensors. Intrinsic and extrinsic calibration are essential steps in sensor fusion. The extrinsic calibration, independent of the sensor's own parameters, and performed after the sensors are installed, greatly determines the accuracy of sensor fusion. Many target-based methods require cumbersome operating procedures and well-designed experimental conditions, making them extremely challenging. To this end, we propose a flexible, easy-to-reproduce and accurate method for extrinsic calibration of 3D radar and camera. The proposed method does not require a specially designed calibration environment, and instead places a single corner reflector (CR) on the ground to iteratively collect radar and camera data simultaneously using Robot Operating System (ROS), and obtain radar-camera point correspondences based on their timestamps, and then use these point correspondences as input to solve the perspective-n-point (PnP) problem, and finally get the extrinsic calibration matrix. Also, RANSAC is used for robustness and the Levenberg-Marquardt (LM) nonlinear optimization algorithm is used for accuracy. Multiple controlled environment experiments as well as real-world experiments demonstrate the efficiency and accuracy (AED error is 15.31 pixels and Acc up to 89\%) of the proposed method.

cs.RO↗

arXiv2021

mmPose-NLP: A Natural Language Processing Approach to Precise Skeletal Pose Estimation using mmWave Radars

In this paper we presented mmPose-NLP, a novel Natural Language Processing (NLP) inspired Sequence-to-Sequence (Seq2Seq) skeletal key-point estimator using millimeter-wave (mmWave) radar data. To the best of the author's knowledge, this is the first method to precisely estimate upto 25 skeletal key-points using mmWave radar data alone. Skeletal pose estimation is critical in several applications ranging from autonomous vehicles, traffic monitoring, patient monitoring, gait analysis, to defense security forensics, and aid both preventative and actionable decision making. The use of mmWave radars for this task, over traditionally employed optical sensors, provide several advantages, primarily its operational robustness to scene lighting and adverse weather conditions, where optical sensor performance degrade significantly. The mmWave radar point-cloud (PCL) data is first voxelized (analogous to tokenization in NLP) and $N$ frames of the voxelized radar data (analogous to a text paragraph in NLP) is subjected to the proposed mmPose-NLP architecture, where the voxel indices of the 25 skeletal key-points (analogous to keyword extraction in NLP) are predicted. The voxel indices are converted back to real world 3-D coordinates using the voxel dictionary used during the tokenization process. Mean Absolute Error (MAE) metrics were used to measure the accuracy of the proposed system against the ground truth, with the proposed mmPose-NLP offering <3 cm localization errors in the depth, horizontal and vertical axes. The effect of the number of input frames vs performance/accuracy was also studied for N = {1,2,..,10}. A comprehensive methodology, results, discussions and limitations are presented in this paper. All the source codes and results are made available on GitHub for furthering research and development in this critical yet emerging domain of skeletal key-point estimation using mmWave radars.

eess.SP↗

arXiv2020

mmFall: Fall Detection using 4D MmWave Radar and a Hybrid Variational RNN AutoEncoder

In this paper we propose mmFall - a novel fall detection system, which comprises of (i) the emerging millimeter-wave (mmWave) radar sensor to collect the human body's point cloud along with the body centroid, and (ii) a variational recurrent autoencoder (VRAE) to compute the anomaly level of the body motion based on the acquired point cloud. A fall is claimed to have occurred when the spike in anomaly level and the drop in centroid height occur simultaneously. The mmWave radar sensor provides several advantages, such as privacycompliance and high-sensitivity to motion, over the traditional sensing modalities. However, (i) randomness in radar point cloud data and (ii) difficulties in fall collection/labeling in the traditional supervised fall detection approaches are the two main challenges. To overcome the randomness in radar data, the proposed VRAE uses variational inference, a probabilistic approach rather than the traditional deterministic approach, to infer the posterior probability of the body's latent motion state at each frame, followed by a recurrent neural network (RNN) to learn the temporal features of the motion over multiple frames. Moreover, to circumvent the difficulties in fall data collection/labeling, the VRAE is built upon an autoencoder architecture in a semi-supervised approach, and trained on only normal activities of daily living (ADL) such that in the inference stage the VRAE will generate a spike in the anomaly level once an abnormal motion, such as fall, occurs. During the experiment, we implemented the VRAE along with two other baselines, and tested on the dataset collected in an apartment. The receiver operating characteristic (ROC) curve indicates that our proposed model outperforms the other two baselines, and achieves 98% detection out of 50 falls at the expense of just 2 false alarms.

cs.LG↗

arXiv2020

MmWave Radar Point Cloud Segmentation using GMM in Multimodal Traffic Monitoring

In multimodal traffic monitoring, we gather traffic statistics for distinct transportation modes, such as pedestrians, cars and bicycles, in order to analyze and improve people's daily mobility in terms of safety and convenience. On account of its robustness to bad light and adverse weather conditions, and inherent speed measurement ability, the radar sensor is a suitable option for this application. However, the sparse radar data from conventional commercial radars make it extremely challenging for transportation mode classification. Thus, we propose to use a high-resolution millimeter-wave(mmWave) radar sensor to obtain a relatively richer radar point cloud representation for a traffic monitoring scenario. Based on a new feature vector, we use the multivariate Gaussian mixture model (GMM) to do the radar point cloud segmentation, i.e. `point-wise' classification, in an unsupervised learning environment. In our experiment, we collected radar point clouds for pedestrians and cars, which also contained the inevitable clutter from the surroundings. The experimental results using GMM on the new feature vector demonstrated a good segmentation performance in terms of the intersection-over-union (IoU) metrics. The detailed methodology and validation metrics are presented and discussed.

eess.SP↗

arXiv2019

mm-Pose: Real-Time Human Skeletal Posture Estimation using mmWave Radars and CNNs

In this paper, mm-Pose, a novel approach to detect and track human skeletons in real-time using an mmWave radar, is proposed. To the best of the authors' knowledge, this is the first method to detect >15 distinct skeletal joints using mmWave radar reflection signals. The proposed method would find several applications in traffic monitoring systems, autonomous vehicles, patient monitoring systems and defense forces to detect and track human skeleton for effective and preventive decision making in real-time. The use of radar makes the system operationally robust to scene lighting and adverse weather conditions. The reflected radar point cloud in range, azimuth and elevation are first resolved and projected in Range-Azimuth and Range-Elevation planes. A novel low-size high-resolution radar-to-image representation is also presented, that overcomes the sparsity in traditional point cloud data and offers significant reduction in the subsequent machine learning architecture. The RGB channels were assigned with the normalized values of range, elevation/azimuth and the power level of the reflection signals for each of the points. A forked CNN architecture was used to predict the real-world position of the skeletal joints in 3-D space, using the radar-to-image representation. The proposed method was tested for a single human scenario for four primary motions, (i) Walking, (ii) Swinging left arm, (iii) Swinging right arm, and (iv) Swinging both arms to validate accurate predictions for motion in range, azimuth and elevation. The detailed methodology, implementation, challenges, and validation results are presented.

eess.SP↗

arXiv2019

Multiple Patients Behavior Detection in Real-time using mmWave Radar and Deep CNNs

To address potential gaps noted in patient monitoring in the hospital, a novel patient behavior detection system using mmWave radar and deep convolution neural network (CNN), which supports the simultaneous recognition of multiple patients' behaviors in real-time, is proposed. In this study, we use an mmWave radar to track multiple patients and detect the scattering point cloud of each one. For each patient, the Doppler pattern of the point cloud over a time period is collected as the behavior signature. A three-layer CNN model is created to classify the behavior for each patient. The tracking and point clouds detection algorithm was also implemented on an mmWave radar hardware platform with an embedded graphics processing unit (GPU) board to collect Doppler pattern and run the CNN model. A training dataset of six types of behavior were collected, over a long duration, to train the model using Adam optimizer with an objective to minimize cross-entropy loss function. Lastly, the system was tested for real-time operation and obtained a very good inference accuracy when predicting each patient's behavior in a two-patient scenario.

eess.SP↗

arXiv2019

Automotive Radar Interference Mitigation Using Adaptive Noise Canceller

Interference among frequency modulated continues wave automotive radars can either increase the noise floor, which occurs in the most cases, or generate a ghost target in rare situations. To address the increment of noise floor due to interference, we proposed a low calculation cost method using adaptive noise canceller to increase the signal-to-interference ratio. In a quadrature receiver, the interference in the positive half of frequency spectrum is correlated to that in the negative half of frequency spectrum, whereas the beat frequencies from real targets are always present in the positive frequency. Thus, we estimated the power of the negative frequency as an indication of interference, and fed the positive frequency and negative frequency components into the primary and reference channel of an adaptive noise canceller, respectively. The least mean square algorithm was used to solve for the optimum filter solution. As a result, both the simulation and experiment showed a good interference mitigation performance.

eess.SP↗