滴滴主题研究计划：计算机视觉专题

精彩资讯，即刻送达

滴滴主题研究计划

计算机视觉专题

三. 多人异常行为预测

1

技术方向

计算机视觉、实例分割、骨架关键点检测、动作识别

2

课题背景

随着计算机和多媒体应用技术的快速发展，大量的监控网络摄像机作为一种有效的措施被广泛地应用,它为人们的社会安全提供了保障。特别在某些特定环境中，例如在车厢、电梯中，基于监控网络摄像机，利用图像分析技术，通过对载客的行为进行识别与检测，自动地智能化预测出其中不正常的行为，并且发出提醒报警信息，保证人们安全，从而减少社会安全事件，保障公民的人身和财产安全。

3

研究目标

针对上述关键问题，研究目标包括不限于以下三个方面：

1.实例分割

近期研究表明，在对未来帧进行语义分割时，在语义层面上的预测，比先预测RGB帧，然后将其分割更加有效。因此，我们探索通过对车厢环境内的图像场景进行实例分割实现冲突预测，在此任务下，希望分割技术达到业界顶级水平。

2.人体骨骼关节点检测

人体骨骼关键点对于描述人体姿态、预测人体行为至关重要，因此人体骨骼关节点检测是诸多计算机视觉任务的基础，例如动作分类、异常行为检测、以及自动驾驶等。通过对关键点检测与分析，实现异常行为识别与预测，保证用户安全。

3.冲突预测

通过机器学习来预测冲突正在成为社会学和计算机交叉领域的一个热议话题。由于导致冲突的因素的不确定性与多变性，导致对冲突预测具有一定挑战性与争议性。期望根据以上研究内容，基于图像实现对多人冲突行为的预测。

四. 图像增强关键技术研究

1

技术方向

计算机视觉、图像增强、暗光增强、去模糊

2

课题背景

图像和视频在公共安全领域发挥越来越大的价值，各地城市安装越来越多的监控摄像头来保障城市的公共安全，企业、生活小区、市场、个人等都安装了摄像头。由于拍摄环境和摄像设备成像质量的影响，往往造成图像/视频的模糊不清晰，对后续图像识别会造成很大的困难和挑战。模糊不清晰来自多个方面，如晚间光照不够、设备成像低分辨率过低、极端天气（雨雾霾等）、图像/视频过度曝光、摄像头对焦不准、物体运动过快等。

3

研究目标

针对上述关键问题，研究目标包括不限于：

1.暗照增强

暗光增强主要解决的是夜晚或光线暗区域拍摄的图像导致人眼或机器“看不清”暗光区域的场景，希望设计基于神经网络的end to end模型，通过暗光增强技术处理暗光图片，输出清晰图片，并在公开测试集上，可以达到最新业界水平。在实际测试集上，经过裁剪优化满足技术落地需求。

2.图像去模糊

图像去模糊一直是图像处理中困扰业界的难题。图像模糊产生的原因可能非常复杂。比如，相机晃动，失焦，拍摄物体高速运动等等。期待希望设计基于神经网络的end to end模型，通过图像增强技术处理模糊图像，输出清晰图片，并在公开测试集上，可以达到最新业界水平。在实际测试集上，经过裁剪优化满足技术落地需求。

3. Multi-PersonAbnormal Behavior Detection

1

Research Area

Computer Vision, Instance Segmentation, Human Key-PointDetection (Pose Estimation, HumanSkeletal System Key-PointDetection), Action Recognition

2

Background

As techniques in machine learning and computer vision are developing rapidly, a wide crosscity network of cameras has been set up to construct a powerful surveillance system which guarantees social security. Using this camera network in conjunction with advanced image analysis techniques, a powerful system can be built to recognize passengers and their actions, thus to discover abnormal human behavior in certain environments such as elevators or vehicles, and warning alarms might be triggered subsequently. This can reduce accidents and protect the safety of people’s lives and property.

3

Target

1. Instance Segmentation

The prediction of future events is an important feature of intelligent behavior, and image prediction is one task falling under such goals. Recent work shows that the semantic prediction of future frames for semantic segmentation is more effective than performing prediction of RGB frames and segmentation separately. Therefore, it is promising to explore a new solution for instance segmentation to alleviate conflicting predictions in a cabin environment.

2. Human Skeletal System KeyPointDetection

Human skeletal system keypoint detection plays an importance role in describing human pose and predicting human behavior, which is the foundation of many computer vision tasks such as action recognition, abnormal behavior detection, and autonomous driving. Through the detection and analysis of key-points, abnormal behavior recognition and prediction can be leveraged to guarantee the safety of passengers.

3. Predicting Conflicts

Predicting conflicts through machine learning is becoming a popular topic in the intersecting fields of sociology and computer sciences. Due to the uncertainty and variability of factors that lead to conflict, conflict prediction is still very controversial within the academic field. With the increase of data resources and computational power, image analysis techniques can be used to predict the probability of conflict between drivers and passengers.

4. Image Enhancement

1

Research Area

Computer Vision, Image Enhancement, Image Deblurring

2

Background

Images and videos are playing an increasingly important role in the field of public safety. More and more surveillance cameras are installed in cities to ensure public safety. These cameras are installed in corporate environments, living quarters, markets, and individual locales etc. Due to the myriad of affecting factors in the shooting environment and the imaging quality of the imaging device, the generated images and videos are often blurry and unclear, which imposes great difficulty and challenge for subsequent image recognition. Blurring can be caused by many factors, such as insufficient night light, low resolution of imaging equipment, extreme weather conditions (rain and fog, etc.), excessive exposure of images/video, inaccurate camera focus, rapid movement of objects, etc.

3

Target

To solve the above key issues, Our research objectives include but are not limited to thefollowing:

1.Dark Image Enhancement

Dark image enhancement mainly resolves scenes where the image is filmed at night or in a dark area. We plan to design an end-to-end model based on deep neural networks to generate clear images through dark image enhancement technologies, and ultimately achieve state-of-the-art performance on open image datasets.The technologies will satisfy all requirements in practical test datasets.

2.Image Blurring

Image blurring has been a persistent issue in the field of image processing. The reasons for image blurring run a wide gamut of complex factors, such as camera shake, imprecise focus, high speed movement of objects, and so on. We plan to design an endtoend model based on deep neural networks to generate clear images through image enhancement on blurred images, and ultimately achieve state-of-the-art performance on open image datasets.In the practical test datasets.The technologies will satisfy all requirements in practical test datasets.

注意