Efficient multiclass object detection: Detecting pedestrians and bicyclists in a truck's blind spot camera

Abstract

In this paper we propose an efficient detection and tracking framework targeting vulnerable road users in the blind spot camera images of a truck. Existing non-vision based safety solutions are not able to handle this problem completely. Therefore we aim to develop an active safety system, based solely on the vision input of the blind spot camera. This is far from trivial: vulnerable road users are a diverse class and consist of a wide variety of poses and appearances. Evidently we need to achieve excellent accuracy results and furthermore we need to cope with the large lens distortion and extreme viewpoints induced by the blind spot camera. In this work we present a multiclass detection methodology which enables the efficient detection of both pedestrians and bicyclists in these challenging images. To achieve this we propose the integration of a warping window approach with multiple object detectors which we intelligently combine in a probabilistic manner. To validate our framework we recorded several simulated dangerous blind spot scenarios with a genuine blind spot camera mounted on a real truck. We show that our approach achieves excellent accuracy on these challenging datasets.

Truck-bicycle safety: an overview of methods of study, risk factors and research needs

“…Several risk factors were identified within the reviewed non-accident studies. These related to road users are behavioural adaptation to safety measures [34], efficiency of mirrors highly depends on the truck driver's alertness [50], challenging scanning of multiple mirrors in high workload situations [55] and truck drivers' overload with physical and cognitive tasks, which affect the driving performance, particularly in turning manoeuvres [51,57]. These related to vehicle are frequent false positive alarms of an active safety system (they are annoying for truck drivers and can cause them to avoid using this system) [50], off-tracking of large trucks in turning manoeuvres (i.e.…”

“…These related to road users are behavioural adaptation to safety measures [34], efficiency of mirrors highly depends on the truck driver's alertness [50], challenging scanning of multiple mirrors in high workload situations [55] and truck drivers' overload with physical and cognitive tasks, which affect the driving performance, particularly in turning manoeuvres [51,57]. These related to vehicle are frequent false positive alarms of an active safety system (they are annoying for truck drivers and can cause them to avoid using this system) [50], off-tracking of large trucks in turning manoeuvres (i.e. the last axle is not able to follow the first axle) results in the truck encroaching on the area where cyclists travel [53,57], sound insulation of the truck cab can contribute to the reduction in drivers situational awareness around their truck [47] and a typical detection system warns only one of the two participants about each other's presence [45].…”

The Automatic Blind Spot Camera: A Vision-Based Active Alarm System

“…As baseline framework we start from the VRU detection and tracking framework for blind spot camera images presented in [16]. An overview of this VRU detection and tracking framework is visualised in fig.…”

“…Additionally, we need to cope with the large viewpoint and lens distortion induced by traditional blind spot cameras. As a starting point, we employ the vanilla implementation of a VRU detection and tracking framework that we proposed in previous work [16], able to efficiently detect and track both pedestrians and bicyclists in these challenging blind spot camera images. However, currently this framework focuses on the aspect of VRU detection and tracking only.…”

“…The remainder of this paper is structured as follows. In section 2 we briefly discuss the vanilla implementation of [16] which we use as our baseline. In section 3 we then discuss our extension, and elevate this baseline framework into a complete active safety system.…”