Haohao Hu

Mr. Haohao Hu

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
20 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Wei TianWei Tian
Wei Tian
XYXianwang Yu
Xianwang Yu
HHHaohao Hu
Haohao Hu
Vision-based identification of lane area and lane marking on the road is an indispensable function for intelligent driving vehicles, especially for localization, mapping and planning tasks. However, due to the increasing complexity of traffic scenes, such as occlusion and discontinuity, detecting lanes and lane markings from an image captured by a monocular camera becomes persistently challenging. The lanes and lane markings have a strong position correlation and are constrained by a spatial geometry prior to the driving scene. Most existing studies only explore a single task, i.e., either lane marking or lane detection, and do not consider the inherent connection or exploit the modeling of this kind of relationship between both elements to improve the detection performance of both tasks. In this paper, we establish a novel multi-task encoder–decoder framework for the simultaneous detection of lanes and lane markings. This approach deploys a dual-branch architecture to extract image information from different scales. By revealing the spatial constraints between lanes and lane markings, we propose an interactive attention learning for their feature information, which involves a Deformable Feature Fusion module for feature encoding, a Cross-Context module as information decoder, a Cross-IoU loss and a Focal-style loss weighting for robust training. Without bells and whistles, our method achieves state-of-the-art results on tasks of lane marking detection (with 32.53% on IoU, 81.61% on accuracy) and lane segmentation (with 91.72% on mIoU) of the BDD100K dataset, which showcases an improvement of 6.33% on IoU, 11.11% on accuracy in lane marking detection and 0.22% on mIoU in lane detection compared to the previous methods.

25 October 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MMMiguel Ángel Muñoz-Bañón
Miguel Ángel Muñoz-Bañón
JPJan-Hendrik Pauls
Jan-Hendrik Pauls
HHHaohao Hu
Haohao Hu
CSChristoph Stiller
Christoph Stiller
Francisco Andrés CandelasFrancisco Andrés Candelas
Francisco Andrés Candelas
Fernando TorresFernando Torres
Fernando Torres
Localization in aerial imagery-based maps offers many advantages, such as global consistency, geo-referenced maps, and the availability of publicly accessible data. However, the landmarks that can be observed from both aerial imagery and on-board sensors is limited. This leads to ambiguities or aliasing during the data association. Building upon a highly informative representation (that allows efficient data association), this paper presents a complete pipeline for resolving these ambiguities. Its core is a robust self-tuning data association that adapts the search area depending on a pseudo-entropy of the measurements. Additionally, to smooth the final result, we adjust the information matrix for the associated data as a function of the relative transform produced by the data association process. We evaluate our method on real data from urban and rural scenarios around the city of Karlsruhe in Germany. We compare state-of-the-art outlier mitigation methods with our self-tuning approach, demonstrating a considerable improvement, especially for outer-urban scenarios.

23 August 2021
Verified
Conference Paper
Closed access
HHHaohao Hu
Haohao Hu
FIFabian Immel
Fabian Immel
JJJohannes Janosovits
Johannes Janosovits
Martin LauerMartin Lauer
Martin Lauer
CSChristoph Stiller
Christoph Stiller
Cuboid objects are widely used in logistics and manufacturing, since they are ideal for automatic manipulation. For that, a reliable detection, identification and tracking algorithm of cuboid objects is a key requirement. RGBD cameras are suited for these tasks, however they suffer from limitations such as occlusions from clutter or a small field of view. A multi RGBD camera setup would remedy many of these limitations. In this work, we present a cuboid detection, identification and tracking system using a multi RGBD camera setup. First, we calibrate our multi camera setup using a robot arm and a colored spherical calibration target. By using spatial and color information, a preprocessing pipeline segments then the unified point cloud into locally connected planar segments. Afterwards, custom spatial criteria allows for assigning the resulting segments to cuboid groups. We present a new modified bounding box regression method to estimate cuboid boxes and a novel intersection over union based approach to track cuboids across frames. By applying our approach, the automatic manipulation and transportation in manufacturing industry will become more efficient, which helps to save more time and cost. Our system is tested and analyzed with a recorded dataset, which contents variant constellations. The reliability and accuracy are demonstrated.

23 July 2021 in Sensors
Verified
Journal Article
Open access
PDF file
HHHaohao Hu
Haohao Hu
JBJohannes Beck
Johannes Beck
Martin LauerMartin Lauer
Martin Lauer
CSChristoph Stiller
Christoph Stiller
The fusion of motion data is key in the fields of robotic and automated driving. Most existing approaches are filter-based or pose-graph-based. By using filter-based approaches, parameters should be set very carefully and the motion data can usually only be fused in a time forward direction. Pose-graph-based approaches can fuse data in time forward and backward directions. However, pre-integration is needed by applying measurements from inertial measurement units. Additionally, both approaches only provide discrete fusion results. In this work, we address this problem and present a uniform B-spline-based continuous fusion approach, which can fuse motion measurements from an inertial measurement unit and pose data from other localization systems robustly, accurately and efficiently. In our continuous fusion approach, an axis-angle is applied as our rotation representation method and uniform B-spline as the back-end optimization base. Evaluation results performed on the real world data show that our approach provides accurate, robust and continuous fusion results, which again supports our continuous fusion concept.

9 January 2022
Verified
Conference Paper
Closed access
NSNa Shen
Na Shen
TWTongyu Wei
Tongyu Wei
HHHaohao Hu
Haohao Hu
WSWilhelm Stork
Wilhelm Stork
This paper presents a novel extrinsic calibration approach for rigid RGB-D cameras with non-overlapping view and UAV, which enables the tracking mission and autonomous flight to support the pilots during the control operation. The checkerboards with QR-marker are used as calibration patterns. Furthermore, a QR code attached on the top of UAV is used to define the UAV reference coordinate system. By importing an additional camera, the overlapping with the two rigid cameras and UAV is created, a 3D structure of calibration patterns is reconstructed from the sequence of images from all cameras by using bundle adjustment algorithm. Simultaneously, the pose of each camera at different frame optimized by minimizing the corresponding 3D projection errors. Furthermore, according the 3D coordinate of the QRcode corners in the reconstructed map, the transformation from UAV reference coordinate system to 3D structure can be obtained. Thus, the extrinsic parameters, i.e. relative position and orientation between fixed cameras and a predefined UAV coordinate system can be determined. The experiments have shown that the presented calibration algorithm provides reliable and accurate results. Meanwhile, the redundancy, reliability, and robustness of the proposed method for different setups of the rigid cameras are evaluated.