Chenhongyi Yang

Computer Science · Boston University · hongyi@bu.edu

I am a second-year master student at Boston University and a research assistant at the Image and Video Computing (IVC) group, where I work with Prof. Margrit Betke and Dr. Vitaly Ablavsky. Prior to that, I received my B.Sc. degree from the University of Science and Technology of China.

Research Experience

Detecting Occluded Objects in Urban Scenes

Supervisors: Prof. Margrit Betke, Dr. Vitaly Ablavsky

  • Proposed a novel bounding box level embedding mechanism: Semantics-Geometry Embedding. The embedding made it possible to determine whether two heavily overlapping boxes belong to the same object.
  • Proposed a new Semantics-Geometry NMS algorithm that was based on the Semantics-Geometry Embedding. It remarkably improved object detection in scenarios with heavy intra-class occlusions.
  • Designed a new object detector: Serial R-FCN. It not only provided the capability to learn the Semantics-Geometry Embedding end-to-end, but also improved object detection accuracy.
  • The proposed method achieved state-of-the-art performance on the task of car detection in the benchmark KITTI dataset and the task of pedestrian detection in the CityPersons dataset by improving the detection recall in heavily-occluded scenes.

Boston University

Reasoning Occlusion Order

Supervisor: Dr. Vitaly Ablavsky

  • Designed the Pairwise Faster R-CNN (PFaster R-CNN), in which the pooled features of overlapping boxes were concatenated and fed into a classification module to predict their depth order.
  • Proposed a rule to construct the depth order matrix for every pair of objects in one image, in which we focused on avoiding redundant computation for the same pair of objects.
  • Helped with generating a synthetic dataset to test the proposed algorithm.

Boston University

Object detection for Satellite Images

Supervisor: Prof. Shouhong Wan

  • Reproduced a Faster R-CNN object detector using Tensorflow, and achieved compatible result with the numbers reported in the Faster R-CNN paper on Pascal VOC 2012 dataset.
  • The detector was used to detect different kinds of house using high-resolution satellite images.

USTC

Relations extraction for Chinese Sentence

Supervisor: Prof. Huanhuan Chen

  • Designed and implemented a relation extractor for Chinese corpus. The extractor was based on template matching where templates were some specific structures of the syntax tree.
  • Trained a SVM classifier to detemine if a extracted relation triple was good. The features used by SVM was handy-crafted by myself.
  • The proposed system was used to help with developing an information retrieval system for building regulations.

USTC

Course Projects

Accelerating AlphaZero-Gomoku with Matrix Computing

CS591: Computational Game Theory

  • Designed a pay-off matrix that can be used by AlphaZero-Gomoku to reduce the number of MCTS, so that the inference speed could be accelerated.
  • PThe Gomoku game was modeled as a two-person zero-sum game, and the payoff matrix for one player was constructed by the average of his winning rate and his opponent's losing rate, which were both predicted by the neural network based on the game state. Then the actual action of the player was produced by computing the best strategy.
  • The accelerated AlphaZero-Gomoku achieved a winning rate of 80% when competing with a pure MCTS agent with 7000 MCTS iterations for one step.

Boston University

Deep 3D Fake Box

CS585: Image and Video Computing

  • Proposed a novel deep learning based algorithm to draw 3D bounding boxes for objects in the 2D images plain called Deep 3D Fake Box.
  • Given the 2D bounding box of an object, the 3D box was constructed by 3 independent parameters that were predicted by a neural network.

Boston University

Minilan Interpreter

Fundamental of Programming Language

  • Developed a Minilan language interpreter that supported variable declaration, arithmetic and bool operations, branch and loop statements for the Minilan programming language.
  • Enabled some advanced function for the interpreter such as garbage collection.

USTC

Publication

Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang, Qi Feng, Margrit Betke: “Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes”, arXiv preprint arXiv:1912.01674 (2019).