Abstract

We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit signifificant overlap/occlusion. A successful approach to modelling the large-scale nature of this problem has been via point process density functions which jointly encode object qualities and spatial interactions. But the corresponding optimisation problem is typically diffificult or intractable, and many of the best current methods rely on Monte Carlo Markov Chain (MCMC) simulation, which converges slowly in a large solution space. We propose an effificient point process inference for largescale object detection using discrete energy minimization. In particular, we approximate the solution space by a fifinite set of object proposals and cast the point process density function to a corresponding energy function of binary variables whose values indicate which object proposals are accepted. We resort to the local submodular approximation (LSA) based trust-region optimisation to fifind the optimal solution. Furthermore we analyse the error of LSA approximation, and show how to adjust the point process energy to dramatically speed up the convergence without harming the optimality. We demonstrate the superior effificiency and accuracy of our method using a variety of large-scale object detection applications such as crowd human detection, birds, cells counting/localization