A coarse-to-fine vehicle detector running in real-time

Castangia, Luca; Grisleri, Paolo; Medici, Paolo; Prioletti, Antonio; Signifredi, Andrea

doi:10.1109/itsc.2014.6957770

Cited by 7 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Caraffi [20] 0.1s Castangia [23] 0.05s YOLO [14] 0.022 SSD500 [15] 0.043 Ours (Without Sparse Windows) 32s Ours 0.025…”

Section: Methodsmentioning

confidence: 99%

“…Caraffi [20] 0.1s Castangia [23] 0.05s YOLO [14] 0.022 SSD500 [15] 0.043 Ours (Without Sparse Windows) 32s Ours 0.025 YOLO [14] SSD500 [15] Ours Fig. 10: Qualitative results on TME motorway dataset in comparison with two state-ofthe-art approaches which are based on deep regression networks.…”

Section: Methods Average Runtimementioning

confidence: 99%

“…Caraffi [20] Castangia [23] YOLO [14] SSD500 [15] Ours (Traditional Weights) Ours Fig. 9: Performance evaluation in different vehicle distances on TME motorway dataset.…”

Section: Recallmentioning

confidence: 99%

See 2 more Smart Citations

Generalized Haar filter based CNN for object detection in traffic scenes

et al. 2017

2017 13th IEEE Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

Vision-based object detection is one of the fundamental functions in numerous traffic scene applications such as self-driving vehicle systems and advance driver assistance systems (ADAS). However, it is also a challenging task due to the diversity of traffic scene and the storage, power and computing source limitations of the platforms for traffic scene applications. This paper presents a generalized Haar filter based deep network which is suitable for the object detection tasks in traffic scene. In this approach, we first decompose a object detection task into several easier local regression tasks. Then, we handle the local regression tasks by using several tiny deep networks which simultaneously output the bounding boxes, categories and confidence scores of detected objects. To reduce the consumption of storage and computing resources, the weights of the deep networks are constrained to the form of generalized Haar filter in training phase. Additionally, we introduce the strategy of sparse windows generation to improve the efficiency of the algorithm. Finally, we perform several experiments to validate the performance of our proposed approach. Experimental results demonstrate that the proposed approach is both efficient and effective in traffic scene compared with the state-of-the-art.

show abstract

“…Caraffi [20] 0.1s Castangia [23] 0.05s YOLO [14] 0.022 SSD500 [15] 0.043 Ours (Without Sparse Windows) 32s Ours 0.025…”

Section: Methodsmentioning

confidence: 99%

Section: Methods Average Runtimementioning

confidence: 99%

See 1 more Smart Citation

Generalized Haar filter based CNN for object detection in traffic scenes

et al. 2017

2017 13th IEEE Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

show abstract

“…One of the key works that supposed a breakthrough is the Viola-Jones algorithm [7], which is based on a sequential classifier with Haar-like features that demonstrated real-time performance on the face detection problem. Since then, researchers have proposed several approaches based on multiple classification algorithms (SVM [8], AdaBoost and variants [9], [6]) and varied features (Haar [10], LBP [6], HOG [8], ICF [9] and ACF [11]).…”

Section: Related Workmentioning

confidence: 99%

“…This work also applies a multi-scale feature preprocessing stage to award more resolution to distant ROIs and reduce processed pixels over 50%, similarly to what is done in the present work. The approach in [9] proposes reducing scales per octave depending on uncertainty from tracked object and giving computation priority to near vehicles. Both works use variants of AdaBoost that early reject regions with low object probability: Boosted Cascade in [8] and Soft-Cascade in [9].…”

Section: Related Workmentioning

confidence: 99%

A Real-Time Multi-scale Vehicle Detection and Tracking Approach for Smartphones

Romera

Bergasa

Arroyo

2015

2015 IEEE 18th International Conference on Intelligent Transportation Systems

View full text Add to dashboard Cite

Automated vehicle detection is a research field in constant evolution due to the new technological advances and security requirements demanded by the current intelligent transportation systems. For these reasons, in this paper we present a vision-based vehicle detection and tracking pipeline, which is able to run on an iPhone in real time. An approach based on smartphone cameras supposes a versatile solution and an alternative to other expensive and complex sensors on the vehicle, such as LiDAR or other range-based methods. A multi-scale proposal and simple geometry consideration of the roads based on the vanishing point are combined to overcome the computational constraints. Our algorithm is tested on a publicly available road dataset, thus demonstrating its real applicability to ADAS or autonomous driving.

show abstract