Wang Hai, Zhu Shilin, Chen Long, Li Yicheng, Luo Tong
School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China.
Automotive Engineering Research Institute, Jiangsu University, Zhenjiang 212013, China.
Sensors (Basel). 2023 Nov 10;23(22):9102. doi: 10.3390/s23229102.
As a fundamental computer vision task, instance segmentation is widely used in the field of autonomous driving because it can perform both instance-level distinction and pixel-level segmentation. We propose CompleteInst based on QueryInst as a solution to the problems of missed detection with a network structure designed from the feature level and the instance level. At the feature level, we propose Global Pyramid Networks (GPN) to collect global information of missed instances. Then, we introduce the semantic branch to complete the semantic features of the missed instances. At the instance level, we implement the query-based optimal transport assignment (OTA-Query) sample allocation strategy which enhances the quality of positive samples of missed instances. Both the semantic branch and OTA-Query are parallel, meaning that there is no interference between stages, and they are compatible with the parallel supervision mechanism of QueryInst. We also compare their performance to that of non-parallel structures, highlighting the superiority of the proposed parallel structure. Experiments were conducted on the Cityscapes and COCO dataset, and the recall of CompleteInst reached 56.7% and 54.2%, a 3.5% and 3.2% improvement over the baseline, outperforming other methods.
作为一项基础的计算机视觉任务，实例分割在自动驾驶领域被广泛应用，因为它既能进行实例级别的区分，又能进行像素级别的分割。我们提出基于QueryInst的CompleteInst，通过从特征级别和实例级别设计网络结构来解决漏检问题。在特征级别，我们提出全局金字塔网络（GPN）来收集漏检实例的全局信息。然后，我们引入语义分支来完善漏检实例的语义特征。在实例级别，我们实现基于查询的最优传输分配（OTA-Query）样本分配策略，该策略提高了漏检实例正样本的质量。语义分支和OTA-Query都是并行的，这意味着各阶段之间没有干扰，并且它们与QueryInst的并行监督机制兼容。我们还将它们的性能与非并行结构的性能进行比较，突出了所提出的并行结构的优越性。在Cityscapes和COCO数据集上进行了实验，CompleteInst的召回率分别达到了56.7%和54.2%，比基线提高了3.5%和3.2%，优于其他方法。
